{
  "best_metric": 10.276288986206055,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.6872852233676976,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003436426116838488,
      "grad_norm": 1.6194039583206177,
      "learning_rate": 1e-05,
      "loss": 41.4894,
      "step": 1
    },
    {
      "epoch": 0.003436426116838488,
      "eval_loss": 10.37592887878418,
      "eval_runtime": 1.6303,
      "eval_samples_per_second": 300.559,
      "eval_steps_per_second": 75.447,
      "step": 1
    },
    {
      "epoch": 0.006872852233676976,
      "grad_norm": 1.5787009000778198,
      "learning_rate": 2e-05,
      "loss": 41.5013,
      "step": 2
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 1.593436598777771,
      "learning_rate": 3e-05,
      "loss": 41.5037,
      "step": 3
    },
    {
      "epoch": 0.013745704467353952,
      "grad_norm": 1.6288071870803833,
      "learning_rate": 4e-05,
      "loss": 41.4974,
      "step": 4
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 1.6095457077026367,
      "learning_rate": 5e-05,
      "loss": 41.4969,
      "step": 5
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 1.645857572555542,
      "learning_rate": 6e-05,
      "loss": 41.4903,
      "step": 6
    },
    {
      "epoch": 0.024054982817869417,
      "grad_norm": 1.6986379623413086,
      "learning_rate": 7e-05,
      "loss": 41.4926,
      "step": 7
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": 1.7210547924041748,
      "learning_rate": 8e-05,
      "loss": 41.49,
      "step": 8
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": 1.7421886920928955,
      "learning_rate": 9e-05,
      "loss": 41.4774,
      "step": 9
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 1.8244717121124268,
      "learning_rate": 0.0001,
      "loss": 41.4644,
      "step": 10
    },
    {
      "epoch": 0.037800687285223365,
      "grad_norm": 1.8427298069000244,
      "learning_rate": 9.999316524962345e-05,
      "loss": 41.4625,
      "step": 11
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 1.852861762046814,
      "learning_rate": 9.997266286704631e-05,
      "loss": 41.4521,
      "step": 12
    },
    {
      "epoch": 0.044673539518900345,
      "grad_norm": 1.9409186840057373,
      "learning_rate": 9.993849845741524e-05,
      "loss": 41.4515,
      "step": 13
    },
    {
      "epoch": 0.048109965635738834,
      "grad_norm": 1.9606143236160278,
      "learning_rate": 9.989068136093873e-05,
      "loss": 41.4291,
      "step": 14
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 2.0019731521606445,
      "learning_rate": 9.98292246503335e-05,
      "loss": 41.4061,
      "step": 15
    },
    {
      "epoch": 0.054982817869415807,
      "grad_norm": 1.9107671976089478,
      "learning_rate": 9.975414512725057e-05,
      "loss": 41.4091,
      "step": 16
    },
    {
      "epoch": 0.058419243986254296,
      "grad_norm": 2.0048282146453857,
      "learning_rate": 9.966546331768191e-05,
      "loss": 41.3934,
      "step": 17
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 2.059582233428955,
      "learning_rate": 9.956320346634876e-05,
      "loss": 41.3918,
      "step": 18
    },
    {
      "epoch": 0.06529209621993128,
      "grad_norm": 2.0314743518829346,
      "learning_rate": 9.944739353007344e-05,
      "loss": 41.3636,
      "step": 19
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 1.9541147947311401,
      "learning_rate": 9.931806517013612e-05,
      "loss": 41.364,
      "step": 20
    },
    {
      "epoch": 0.07216494845360824,
      "grad_norm": 2.1738221645355225,
      "learning_rate": 9.917525374361912e-05,
      "loss": 41.3279,
      "step": 21
    },
    {
      "epoch": 0.07560137457044673,
      "grad_norm": 2.0624327659606934,
      "learning_rate": 9.901899829374047e-05,
      "loss": 41.3355,
      "step": 22
    },
    {
      "epoch": 0.07903780068728522,
      "grad_norm": 1.984593391418457,
      "learning_rate": 9.884934153917997e-05,
      "loss": 41.3312,
      "step": 23
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 1.857358694076538,
      "learning_rate": 9.86663298624003e-05,
      "loss": 41.3073,
      "step": 24
    },
    {
      "epoch": 0.0859106529209622,
      "grad_norm": 1.8403151035308838,
      "learning_rate": 9.847001329696653e-05,
      "loss": 41.316,
      "step": 25
    },
    {
      "epoch": 0.08934707903780069,
      "grad_norm": 1.7378275394439697,
      "learning_rate": 9.826044551386744e-05,
      "loss": 41.3077,
      "step": 26
    },
    {
      "epoch": 0.09278350515463918,
      "grad_norm": 1.7155497074127197,
      "learning_rate": 9.803768380684242e-05,
      "loss": 41.2925,
      "step": 27
    },
    {
      "epoch": 0.09621993127147767,
      "grad_norm": 1.6373707056045532,
      "learning_rate": 9.780178907671789e-05,
      "loss": 41.2924,
      "step": 28
    },
    {
      "epoch": 0.09965635738831616,
      "grad_norm": 1.5444339513778687,
      "learning_rate": 9.755282581475769e-05,
      "loss": 41.2894,
      "step": 29
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 1.453321099281311,
      "learning_rate": 9.729086208503174e-05,
      "loss": 41.2705,
      "step": 30
    },
    {
      "epoch": 0.10652920962199312,
      "grad_norm": 1.4121428728103638,
      "learning_rate": 9.701596950580806e-05,
      "loss": 41.2565,
      "step": 31
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 1.3248140811920166,
      "learning_rate": 9.672822322997305e-05,
      "loss": 41.2464,
      "step": 32
    },
    {
      "epoch": 0.1134020618556701,
      "grad_norm": 1.2759703397750854,
      "learning_rate": 9.642770192448536e-05,
      "loss": 41.2352,
      "step": 33
    },
    {
      "epoch": 0.11683848797250859,
      "grad_norm": 1.1593044996261597,
      "learning_rate": 9.611448774886924e-05,
      "loss": 41.2383,
      "step": 34
    },
    {
      "epoch": 0.12027491408934708,
      "grad_norm": 1.0898247957229614,
      "learning_rate": 9.578866633275288e-05,
      "loss": 41.2257,
      "step": 35
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 1.069875717163086,
      "learning_rate": 9.545032675245813e-05,
      "loss": 41.2191,
      "step": 36
    },
    {
      "epoch": 0.12714776632302405,
      "grad_norm": 1.0196983814239502,
      "learning_rate": 9.509956150664796e-05,
      "loss": 41.2059,
      "step": 37
    },
    {
      "epoch": 0.13058419243986255,
      "grad_norm": 0.9522327184677124,
      "learning_rate": 9.473646649103818e-05,
      "loss": 41.1988,
      "step": 38
    },
    {
      "epoch": 0.13402061855670103,
      "grad_norm": 0.9046036005020142,
      "learning_rate": 9.43611409721806e-05,
      "loss": 41.2013,
      "step": 39
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 0.8106074929237366,
      "learning_rate": 9.397368756032445e-05,
      "loss": 41.2138,
      "step": 40
    },
    {
      "epoch": 0.140893470790378,
      "grad_norm": 0.7380366921424866,
      "learning_rate": 9.357421218136386e-05,
      "loss": 41.1967,
      "step": 41
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 0.862231969833374,
      "learning_rate": 9.316282404787871e-05,
      "loss": 41.1894,
      "step": 42
    },
    {
      "epoch": 0.14776632302405499,
      "grad_norm": 0.6930814385414124,
      "learning_rate": 9.273963562927695e-05,
      "loss": 41.1908,
      "step": 43
    },
    {
      "epoch": 0.15120274914089346,
      "grad_norm": 0.6951217651367188,
      "learning_rate": 9.230476262104677e-05,
      "loss": 41.178,
      "step": 44
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 0.5928729772567749,
      "learning_rate": 9.185832391312644e-05,
      "loss": 41.1689,
      "step": 45
    },
    {
      "epoch": 0.15807560137457044,
      "grad_norm": 0.5835124850273132,
      "learning_rate": 9.140044155740101e-05,
      "loss": 41.1812,
      "step": 46
    },
    {
      "epoch": 0.16151202749140894,
      "grad_norm": 0.5159205794334412,
      "learning_rate": 9.093124073433463e-05,
      "loss": 41.1828,
      "step": 47
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.5052924156188965,
      "learning_rate": 9.045084971874738e-05,
      "loss": 41.1794,
      "step": 48
    },
    {
      "epoch": 0.16838487972508592,
      "grad_norm": 0.6070402264595032,
      "learning_rate": 8.995939984474624e-05,
      "loss": 41.1968,
      "step": 49
    },
    {
      "epoch": 0.1718213058419244,
      "grad_norm": 0.7916432619094849,
      "learning_rate": 8.945702546981969e-05,
      "loss": 41.2031,
      "step": 50
    },
    {
      "epoch": 0.1718213058419244,
      "eval_loss": 10.293122291564941,
      "eval_runtime": 1.6386,
      "eval_samples_per_second": 299.036,
      "eval_steps_per_second": 75.064,
      "step": 50
    },
    {
      "epoch": 0.17525773195876287,
      "grad_norm": 0.5261642336845398,
      "learning_rate": 8.894386393810563e-05,
      "loss": 41.1844,
      "step": 51
    },
    {
      "epoch": 0.17869415807560138,
      "grad_norm": 0.4562110900878906,
      "learning_rate": 8.842005554284296e-05,
      "loss": 41.1685,
      "step": 52
    },
    {
      "epoch": 0.18213058419243985,
      "grad_norm": 0.45629674196243286,
      "learning_rate": 8.788574348801675e-05,
      "loss": 41.169,
      "step": 53
    },
    {
      "epoch": 0.18556701030927836,
      "grad_norm": 0.4887603521347046,
      "learning_rate": 8.73410738492077e-05,
      "loss": 41.1667,
      "step": 54
    },
    {
      "epoch": 0.18900343642611683,
      "grad_norm": 0.39215928316116333,
      "learning_rate": 8.678619553365659e-05,
      "loss": 41.1747,
      "step": 55
    },
    {
      "epoch": 0.19243986254295534,
      "grad_norm": 0.31313490867614746,
      "learning_rate": 8.622126023955446e-05,
      "loss": 41.1781,
      "step": 56
    },
    {
      "epoch": 0.1958762886597938,
      "grad_norm": 0.2914177477359772,
      "learning_rate": 8.564642241456986e-05,
      "loss": 41.166,
      "step": 57
    },
    {
      "epoch": 0.19931271477663232,
      "grad_norm": 0.32502812147140503,
      "learning_rate": 8.506183921362443e-05,
      "loss": 41.1648,
      "step": 58
    },
    {
      "epoch": 0.2027491408934708,
      "grad_norm": 0.26807987689971924,
      "learning_rate": 8.44676704559283e-05,
      "loss": 41.164,
      "step": 59
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.27264660596847534,
      "learning_rate": 8.386407858128706e-05,
      "loss": 41.1556,
      "step": 60
    },
    {
      "epoch": 0.20962199312714777,
      "grad_norm": 0.2628459632396698,
      "learning_rate": 8.32512286056924e-05,
      "loss": 41.1569,
      "step": 61
    },
    {
      "epoch": 0.21305841924398625,
      "grad_norm": 0.2567909061908722,
      "learning_rate": 8.262928807620843e-05,
      "loss": 41.1592,
      "step": 62
    },
    {
      "epoch": 0.21649484536082475,
      "grad_norm": 0.25221773982048035,
      "learning_rate": 8.199842702516583e-05,
      "loss": 41.1671,
      "step": 63
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": 0.2868829369544983,
      "learning_rate": 8.135881792367686e-05,
      "loss": 41.165,
      "step": 64
    },
    {
      "epoch": 0.22336769759450173,
      "grad_norm": 0.20182664692401886,
      "learning_rate": 8.07106356344834e-05,
      "loss": 41.1398,
      "step": 65
    },
    {
      "epoch": 0.2268041237113402,
      "grad_norm": 0.2342250794172287,
      "learning_rate": 8.005405736415126e-05,
      "loss": 41.1566,
      "step": 66
    },
    {
      "epoch": 0.23024054982817868,
      "grad_norm": 0.1995733380317688,
      "learning_rate": 7.938926261462366e-05,
      "loss": 41.1453,
      "step": 67
    },
    {
      "epoch": 0.23367697594501718,
      "grad_norm": 0.2241991013288498,
      "learning_rate": 7.871643313414718e-05,
      "loss": 41.1501,
      "step": 68
    },
    {
      "epoch": 0.23711340206185566,
      "grad_norm": 0.25401216745376587,
      "learning_rate": 7.803575286758364e-05,
      "loss": 41.148,
      "step": 69
    },
    {
      "epoch": 0.24054982817869416,
      "grad_norm": 0.2290734052658081,
      "learning_rate": 7.734740790612136e-05,
      "loss": 41.1445,
      "step": 70
    },
    {
      "epoch": 0.24398625429553264,
      "grad_norm": 0.26713621616363525,
      "learning_rate": 7.66515864363997e-05,
      "loss": 41.1618,
      "step": 71
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 0.30236026644706726,
      "learning_rate": 7.594847868906076e-05,
      "loss": 41.1588,
      "step": 72
    },
    {
      "epoch": 0.2508591065292096,
      "grad_norm": 0.32867515087127686,
      "learning_rate": 7.52382768867422e-05,
      "loss": 41.1578,
      "step": 73
    },
    {
      "epoch": 0.2542955326460481,
      "grad_norm": 0.3131564259529114,
      "learning_rate": 7.452117519152542e-05,
      "loss": 41.1481,
      "step": 74
    },
    {
      "epoch": 0.25773195876288657,
      "grad_norm": 0.23836350440979004,
      "learning_rate": 7.379736965185368e-05,
      "loss": 41.1555,
      "step": 75
    },
    {
      "epoch": 0.2611683848797251,
      "grad_norm": 0.22223691642284393,
      "learning_rate": 7.30670581489344e-05,
      "loss": 41.1674,
      "step": 76
    },
    {
      "epoch": 0.2646048109965636,
      "grad_norm": 0.25590258836746216,
      "learning_rate": 7.233044034264034e-05,
      "loss": 41.1525,
      "step": 77
    },
    {
      "epoch": 0.26804123711340205,
      "grad_norm": 0.3536461293697357,
      "learning_rate": 7.158771761692464e-05,
      "loss": 41.1672,
      "step": 78
    },
    {
      "epoch": 0.27147766323024053,
      "grad_norm": 0.22657400369644165,
      "learning_rate": 7.083909302476453e-05,
      "loss": 41.153,
      "step": 79
    },
    {
      "epoch": 0.27491408934707906,
      "grad_norm": 0.31488490104675293,
      "learning_rate": 7.008477123264848e-05,
      "loss": 41.1599,
      "step": 80
    },
    {
      "epoch": 0.27835051546391754,
      "grad_norm": 0.23108160495758057,
      "learning_rate": 6.932495846462261e-05,
      "loss": 41.1571,
      "step": 81
    },
    {
      "epoch": 0.281786941580756,
      "grad_norm": 0.25782522559165955,
      "learning_rate": 6.855986244591104e-05,
      "loss": 41.1554,
      "step": 82
    },
    {
      "epoch": 0.2852233676975945,
      "grad_norm": 0.2192448377609253,
      "learning_rate": 6.778969234612584e-05,
      "loss": 41.1658,
      "step": 83
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 0.24031920731067657,
      "learning_rate": 6.701465872208216e-05,
      "loss": 41.1555,
      "step": 84
    },
    {
      "epoch": 0.2920962199312715,
      "grad_norm": 0.24178466200828552,
      "learning_rate": 6.623497346023418e-05,
      "loss": 41.1618,
      "step": 85
    },
    {
      "epoch": 0.29553264604810997,
      "grad_norm": 0.23651190102100372,
      "learning_rate": 6.545084971874738e-05,
      "loss": 41.1333,
      "step": 86
    },
    {
      "epoch": 0.29896907216494845,
      "grad_norm": 0.25855401158332825,
      "learning_rate": 6.466250186922325e-05,
      "loss": 41.1709,
      "step": 87
    },
    {
      "epoch": 0.3024054982817869,
      "grad_norm": 0.2338763177394867,
      "learning_rate": 6.387014543809223e-05,
      "loss": 41.1532,
      "step": 88
    },
    {
      "epoch": 0.30584192439862545,
      "grad_norm": 0.24783508479595184,
      "learning_rate": 6.307399704769099e-05,
      "loss": 41.1521,
      "step": 89
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 0.2462136298418045,
      "learning_rate": 6.227427435703997e-05,
      "loss": 41.1571,
      "step": 90
    },
    {
      "epoch": 0.3127147766323024,
      "grad_norm": 0.3009977638721466,
      "learning_rate": 6.147119600233758e-05,
      "loss": 41.1431,
      "step": 91
    },
    {
      "epoch": 0.3161512027491409,
      "grad_norm": 0.24368557333946228,
      "learning_rate": 6.066498153718735e-05,
      "loss": 41.1548,
      "step": 92
    },
    {
      "epoch": 0.31958762886597936,
      "grad_norm": 0.24215248227119446,
      "learning_rate": 5.985585137257401e-05,
      "loss": 41.1537,
      "step": 93
    },
    {
      "epoch": 0.3230240549828179,
      "grad_norm": 0.27010664343833923,
      "learning_rate": 5.90440267166055e-05,
      "loss": 41.1488,
      "step": 94
    },
    {
      "epoch": 0.32646048109965636,
      "grad_norm": 0.24635644257068634,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 41.1627,
      "step": 95
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 0.3010130524635315,
      "learning_rate": 5.74131823855921e-05,
      "loss": 41.1523,
      "step": 96
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.28352296352386475,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 41.1528,
      "step": 97
    },
    {
      "epoch": 0.33676975945017185,
      "grad_norm": 0.24886541068553925,
      "learning_rate": 5.577423184847932e-05,
      "loss": 41.151,
      "step": 98
    },
    {
      "epoch": 0.3402061855670103,
      "grad_norm": 0.23849250376224518,
      "learning_rate": 5.495227651252315e-05,
      "loss": 41.1472,
      "step": 99
    },
    {
      "epoch": 0.3436426116838488,
      "grad_norm": 0.4648593068122864,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 41.1737,
      "step": 100
    },
    {
      "epoch": 0.3436426116838488,
      "eval_loss": 10.286445617675781,
      "eval_runtime": 1.7262,
      "eval_samples_per_second": 283.867,
      "eval_steps_per_second": 71.256,
      "step": 100
    },
    {
      "epoch": 0.3470790378006873,
      "grad_norm": 0.44046932458877563,
      "learning_rate": 5.330452921628497e-05,
      "loss": 41.1574,
      "step": 101
    },
    {
      "epoch": 0.35051546391752575,
      "grad_norm": 0.3719726800918579,
      "learning_rate": 5.247918773366112e-05,
      "loss": 41.1377,
      "step": 102
    },
    {
      "epoch": 0.3539518900343643,
      "grad_norm": 0.4948846697807312,
      "learning_rate": 5.165316846586541e-05,
      "loss": 41.13,
      "step": 103
    },
    {
      "epoch": 0.35738831615120276,
      "grad_norm": 0.38370922207832336,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 41.1388,
      "step": 104
    },
    {
      "epoch": 0.36082474226804123,
      "grad_norm": 0.34370988607406616,
      "learning_rate": 5e-05,
      "loss": 41.1536,
      "step": 105
    },
    {
      "epoch": 0.3642611683848797,
      "grad_norm": 0.37829169631004333,
      "learning_rate": 4.917330276168208e-05,
      "loss": 41.1235,
      "step": 106
    },
    {
      "epoch": 0.36769759450171824,
      "grad_norm": 0.3951474726200104,
      "learning_rate": 4.834683153413459e-05,
      "loss": 41.1367,
      "step": 107
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 0.3563172519207001,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 41.1338,
      "step": 108
    },
    {
      "epoch": 0.3745704467353952,
      "grad_norm": 0.4187951683998108,
      "learning_rate": 4.669547078371504e-05,
      "loss": 41.1201,
      "step": 109
    },
    {
      "epoch": 0.37800687285223367,
      "grad_norm": 0.36119821667671204,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 41.1228,
      "step": 110
    },
    {
      "epoch": 0.38144329896907214,
      "grad_norm": 0.39495307207107544,
      "learning_rate": 4.504772348747687e-05,
      "loss": 41.1262,
      "step": 111
    },
    {
      "epoch": 0.3848797250859107,
      "grad_norm": 0.387360155582428,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 41.1264,
      "step": 112
    },
    {
      "epoch": 0.38831615120274915,
      "grad_norm": 0.3668377101421356,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 41.1105,
      "step": 113
    },
    {
      "epoch": 0.3917525773195876,
      "grad_norm": 0.372389018535614,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 41.1135,
      "step": 114
    },
    {
      "epoch": 0.3951890034364261,
      "grad_norm": 0.3370439112186432,
      "learning_rate": 4.17702704859633e-05,
      "loss": 41.1309,
      "step": 115
    },
    {
      "epoch": 0.39862542955326463,
      "grad_norm": 0.32661306858062744,
      "learning_rate": 4.095597328339452e-05,
      "loss": 41.1335,
      "step": 116
    },
    {
      "epoch": 0.4020618556701031,
      "grad_norm": 0.39608657360076904,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 41.1053,
      "step": 117
    },
    {
      "epoch": 0.4054982817869416,
      "grad_norm": 0.32898077368736267,
      "learning_rate": 3.933501846281267e-05,
      "loss": 41.1216,
      "step": 118
    },
    {
      "epoch": 0.40893470790378006,
      "grad_norm": 0.3393823206424713,
      "learning_rate": 3.852880399766243e-05,
      "loss": 41.1193,
      "step": 119
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 0.33924928307533264,
      "learning_rate": 3.772572564296005e-05,
      "loss": 41.1468,
      "step": 120
    },
    {
      "epoch": 0.41580756013745707,
      "grad_norm": 0.32331833243370056,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 41.1337,
      "step": 121
    },
    {
      "epoch": 0.41924398625429554,
      "grad_norm": 0.4072739779949188,
      "learning_rate": 3.612985456190778e-05,
      "loss": 41.1126,
      "step": 122
    },
    {
      "epoch": 0.422680412371134,
      "grad_norm": 0.3906877040863037,
      "learning_rate": 3.533749813077677e-05,
      "loss": 41.1388,
      "step": 123
    },
    {
      "epoch": 0.4261168384879725,
      "grad_norm": 0.3272218406200409,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 41.1382,
      "step": 124
    },
    {
      "epoch": 0.42955326460481097,
      "grad_norm": 0.3604068458080292,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 41.1173,
      "step": 125
    },
    {
      "epoch": 0.4329896907216495,
      "grad_norm": 0.3931737244129181,
      "learning_rate": 3.298534127791785e-05,
      "loss": 41.1045,
      "step": 126
    },
    {
      "epoch": 0.436426116838488,
      "grad_norm": 0.39649155735969543,
      "learning_rate": 3.221030765387417e-05,
      "loss": 41.1335,
      "step": 127
    },
    {
      "epoch": 0.43986254295532645,
      "grad_norm": 0.4722374975681305,
      "learning_rate": 3.144013755408895e-05,
      "loss": 41.1519,
      "step": 128
    },
    {
      "epoch": 0.44329896907216493,
      "grad_norm": 0.49732741713523865,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 41.1344,
      "step": 129
    },
    {
      "epoch": 0.44673539518900346,
      "grad_norm": 0.3865332007408142,
      "learning_rate": 2.991522876735154e-05,
      "loss": 41.1336,
      "step": 130
    },
    {
      "epoch": 0.45017182130584193,
      "grad_norm": 0.4043004810810089,
      "learning_rate": 2.916090697523549e-05,
      "loss": 41.1347,
      "step": 131
    },
    {
      "epoch": 0.4536082474226804,
      "grad_norm": 0.34646517038345337,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 41.1082,
      "step": 132
    },
    {
      "epoch": 0.4570446735395189,
      "grad_norm": 0.3011385500431061,
      "learning_rate": 2.766955965735968e-05,
      "loss": 41.1187,
      "step": 133
    },
    {
      "epoch": 0.46048109965635736,
      "grad_norm": 0.2969728410243988,
      "learning_rate": 2.693294185106562e-05,
      "loss": 41.1409,
      "step": 134
    },
    {
      "epoch": 0.4639175257731959,
      "grad_norm": 0.3384009301662445,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 41.1167,
      "step": 135
    },
    {
      "epoch": 0.46735395189003437,
      "grad_norm": 0.3394676446914673,
      "learning_rate": 2.547882480847461e-05,
      "loss": 41.1196,
      "step": 136
    },
    {
      "epoch": 0.47079037800687284,
      "grad_norm": 0.343344122171402,
      "learning_rate": 2.476172311325783e-05,
      "loss": 41.1004,
      "step": 137
    },
    {
      "epoch": 0.4742268041237113,
      "grad_norm": 0.31243452429771423,
      "learning_rate": 2.405152131093926e-05,
      "loss": 41.119,
      "step": 138
    },
    {
      "epoch": 0.47766323024054985,
      "grad_norm": 0.2887789309024811,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 41.1261,
      "step": 139
    },
    {
      "epoch": 0.48109965635738833,
      "grad_norm": 0.31578800082206726,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 41.1116,
      "step": 140
    },
    {
      "epoch": 0.4845360824742268,
      "grad_norm": 0.30414605140686035,
      "learning_rate": 2.196424713241637e-05,
      "loss": 41.121,
      "step": 141
    },
    {
      "epoch": 0.4879725085910653,
      "grad_norm": 0.31922322511672974,
      "learning_rate": 2.128356686585282e-05,
      "loss": 41.1203,
      "step": 142
    },
    {
      "epoch": 0.49140893470790376,
      "grad_norm": 0.29430297017097473,
      "learning_rate": 2.061073738537635e-05,
      "loss": 41.108,
      "step": 143
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 0.31622546911239624,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 41.1317,
      "step": 144
    },
    {
      "epoch": 0.49828178694158076,
      "grad_norm": 0.31011977791786194,
      "learning_rate": 1.928936436551661e-05,
      "loss": 41.1443,
      "step": 145
    },
    {
      "epoch": 0.5017182130584192,
      "grad_norm": 0.35643208026885986,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 41.1305,
      "step": 146
    },
    {
      "epoch": 0.5051546391752577,
      "grad_norm": 0.35247841477394104,
      "learning_rate": 1.800157297483417e-05,
      "loss": 41.1393,
      "step": 147
    },
    {
      "epoch": 0.5085910652920962,
      "grad_norm": 0.3502804636955261,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 41.1501,
      "step": 148
    },
    {
      "epoch": 0.5120274914089347,
      "grad_norm": 0.361873596906662,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 41.1272,
      "step": 149
    },
    {
      "epoch": 0.5154639175257731,
      "grad_norm": 0.7327353954315186,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 41.1591,
      "step": 150
    },
    {
      "epoch": 0.5154639175257731,
      "eval_loss": 10.278097152709961,
      "eval_runtime": 1.6359,
      "eval_samples_per_second": 299.53,
      "eval_steps_per_second": 75.188,
      "step": 150
    },
    {
      "epoch": 0.5189003436426117,
      "grad_norm": 0.5851008296012878,
      "learning_rate": 1.553232954407171e-05,
      "loss": 41.1202,
      "step": 151
    },
    {
      "epoch": 0.5223367697594502,
      "grad_norm": 0.4855727255344391,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 41.1165,
      "step": 152
    },
    {
      "epoch": 0.5257731958762887,
      "grad_norm": 0.49356281757354736,
      "learning_rate": 1.435357758543015e-05,
      "loss": 41.109,
      "step": 153
    },
    {
      "epoch": 0.5292096219931272,
      "grad_norm": 0.4921821653842926,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 41.0982,
      "step": 154
    },
    {
      "epoch": 0.5326460481099656,
      "grad_norm": 0.512711763381958,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 41.0965,
      "step": 155
    },
    {
      "epoch": 0.5360824742268041,
      "grad_norm": 0.49019694328308105,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 41.1135,
      "step": 156
    },
    {
      "epoch": 0.5395189003436426,
      "grad_norm": 0.4963749945163727,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 41.1083,
      "step": 157
    },
    {
      "epoch": 0.5429553264604811,
      "grad_norm": 0.4590628445148468,
      "learning_rate": 1.157994445715706e-05,
      "loss": 41.1001,
      "step": 158
    },
    {
      "epoch": 0.5463917525773195,
      "grad_norm": 0.4449896514415741,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 41.1081,
      "step": 159
    },
    {
      "epoch": 0.5498281786941581,
      "grad_norm": 0.4847472608089447,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 41.0887,
      "step": 160
    },
    {
      "epoch": 0.5532646048109966,
      "grad_norm": 0.4499075710773468,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 41.0831,
      "step": 161
    },
    {
      "epoch": 0.5567010309278351,
      "grad_norm": 0.4177559018135071,
      "learning_rate": 9.549150281252633e-06,
      "loss": 41.0946,
      "step": 162
    },
    {
      "epoch": 0.5601374570446735,
      "grad_norm": 0.4087377190589905,
      "learning_rate": 9.068759265665384e-06,
      "loss": 41.1076,
      "step": 163
    },
    {
      "epoch": 0.563573883161512,
      "grad_norm": 0.4660016596317291,
      "learning_rate": 8.599558442598998e-06,
      "loss": 41.091,
      "step": 164
    },
    {
      "epoch": 0.5670103092783505,
      "grad_norm": 0.41510921716690063,
      "learning_rate": 8.141676086873572e-06,
      "loss": 41.0795,
      "step": 165
    },
    {
      "epoch": 0.570446735395189,
      "grad_norm": 0.3653230667114258,
      "learning_rate": 7.695237378953223e-06,
      "loss": 41.0835,
      "step": 166
    },
    {
      "epoch": 0.5738831615120275,
      "grad_norm": 0.3499058783054352,
      "learning_rate": 7.260364370723044e-06,
      "loss": 41.102,
      "step": 167
    },
    {
      "epoch": 0.5773195876288659,
      "grad_norm": 0.404680460691452,
      "learning_rate": 6.837175952121306e-06,
      "loss": 41.0909,
      "step": 168
    },
    {
      "epoch": 0.5807560137457045,
      "grad_norm": 0.4175773561000824,
      "learning_rate": 6.425787818636131e-06,
      "loss": 41.1108,
      "step": 169
    },
    {
      "epoch": 0.584192439862543,
      "grad_norm": 0.41201725602149963,
      "learning_rate": 6.026312439675552e-06,
      "loss": 41.0814,
      "step": 170
    },
    {
      "epoch": 0.5876288659793815,
      "grad_norm": 0.32929545640945435,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 41.1086,
      "step": 171
    },
    {
      "epoch": 0.5910652920962199,
      "grad_norm": 0.3038809299468994,
      "learning_rate": 5.263533508961827e-06,
      "loss": 41.107,
      "step": 172
    },
    {
      "epoch": 0.5945017182130584,
      "grad_norm": 0.384991854429245,
      "learning_rate": 4.900438493352055e-06,
      "loss": 41.1008,
      "step": 173
    },
    {
      "epoch": 0.5979381443298969,
      "grad_norm": 0.3318168818950653,
      "learning_rate": 4.549673247541875e-06,
      "loss": 41.1108,
      "step": 174
    },
    {
      "epoch": 0.6013745704467354,
      "grad_norm": 0.3740953505039215,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 41.1035,
      "step": 175
    },
    {
      "epoch": 0.6048109965635738,
      "grad_norm": 0.33406805992126465,
      "learning_rate": 3.885512251130763e-06,
      "loss": 41.1152,
      "step": 176
    },
    {
      "epoch": 0.6082474226804123,
      "grad_norm": 0.3532574772834778,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 41.1093,
      "step": 177
    },
    {
      "epoch": 0.6116838487972509,
      "grad_norm": 0.3701534569263458,
      "learning_rate": 3.271776770026963e-06,
      "loss": 41.1401,
      "step": 178
    },
    {
      "epoch": 0.6151202749140894,
      "grad_norm": 0.48316454887390137,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 41.1233,
      "step": 179
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 0.5432168841362,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 41.1487,
      "step": 180
    },
    {
      "epoch": 0.6219931271477663,
      "grad_norm": 0.38009095191955566,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 41.1051,
      "step": 181
    },
    {
      "epoch": 0.6254295532646048,
      "grad_norm": 0.393370658159256,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 41.1135,
      "step": 182
    },
    {
      "epoch": 0.6288659793814433,
      "grad_norm": 0.33339303731918335,
      "learning_rate": 1.962316193157593e-06,
      "loss": 41.105,
      "step": 183
    },
    {
      "epoch": 0.6323024054982818,
      "grad_norm": 0.37761175632476807,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 41.1037,
      "step": 184
    },
    {
      "epoch": 0.6357388316151202,
      "grad_norm": 0.3638911247253418,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 41.1088,
      "step": 185
    },
    {
      "epoch": 0.6391752577319587,
      "grad_norm": 0.344001829624176,
      "learning_rate": 1.333670137599713e-06,
      "loss": 41.1098,
      "step": 186
    },
    {
      "epoch": 0.6426116838487973,
      "grad_norm": 0.395137757062912,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 41.0979,
      "step": 187
    },
    {
      "epoch": 0.6460481099656358,
      "grad_norm": 0.3118741810321808,
      "learning_rate": 9.810017062595322e-07,
      "loss": 41.1019,
      "step": 188
    },
    {
      "epoch": 0.6494845360824743,
      "grad_norm": 0.32943135499954224,
      "learning_rate": 8.247462563808817e-07,
      "loss": 41.1157,
      "step": 189
    },
    {
      "epoch": 0.6529209621993127,
      "grad_norm": 0.31059110164642334,
      "learning_rate": 6.819348298638839e-07,
      "loss": 41.1005,
      "step": 190
    },
    {
      "epoch": 0.6563573883161512,
      "grad_norm": 0.3603702783584595,
      "learning_rate": 5.526064699265753e-07,
      "loss": 41.1022,
      "step": 191
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": 0.3580923080444336,
      "learning_rate": 4.367965336512403e-07,
      "loss": 41.1208,
      "step": 192
    },
    {
      "epoch": 0.6632302405498282,
      "grad_norm": 0.32063210010528564,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 41.1122,
      "step": 193
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.39908280968666077,
      "learning_rate": 2.458548727494292e-07,
      "loss": 41.0969,
      "step": 194
    },
    {
      "epoch": 0.6701030927835051,
      "grad_norm": 0.3361837565898895,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 41.1089,
      "step": 195
    },
    {
      "epoch": 0.6735395189003437,
      "grad_norm": 0.3954990804195404,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 41.1171,
      "step": 196
    },
    {
      "epoch": 0.6769759450171822,
      "grad_norm": 0.36021673679351807,
      "learning_rate": 6.150154258476315e-08,
      "loss": 41.1212,
      "step": 197
    },
    {
      "epoch": 0.6804123711340206,
      "grad_norm": 0.3594377636909485,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 41.1111,
      "step": 198
    },
    {
      "epoch": 0.6838487972508591,
      "grad_norm": 0.4275110065937042,
      "learning_rate": 6.834750376549792e-09,
      "loss": 41.1274,
      "step": 199
    },
    {
      "epoch": 0.6872852233676976,
      "grad_norm": 0.7817481756210327,
      "learning_rate": 0.0,
      "loss": 41.1589,
      "step": 200
    },
    {
      "epoch": 0.6872852233676976,
      "eval_loss": 10.276288986206055,
      "eval_runtime": 1.6369,
      "eval_samples_per_second": 299.346,
      "eval_steps_per_second": 75.142,
      "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": 73948060975104.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}