{
  "best_metric": 1.339756965637207,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 2.18978102189781,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014598540145985401,
      "grad_norm": 0.33531391620635986,
      "learning_rate": 1e-05,
      "loss": 1.181,
      "step": 1
    },
    {
      "epoch": 0.014598540145985401,
      "eval_loss": 1.5133534669876099,
      "eval_runtime": 9.3298,
      "eval_samples_per_second": 12.433,
      "eval_steps_per_second": 3.108,
      "step": 1
    },
    {
      "epoch": 0.029197080291970802,
      "grad_norm": 0.2277866154909134,
      "learning_rate": 2e-05,
      "loss": 1.4452,
      "step": 2
    },
    {
      "epoch": 0.043795620437956206,
      "grad_norm": 0.3821689486503601,
      "learning_rate": 3e-05,
      "loss": 1.4238,
      "step": 3
    },
    {
      "epoch": 0.058394160583941604,
      "grad_norm": 0.2636841833591461,
      "learning_rate": 4e-05,
      "loss": 1.4073,
      "step": 4
    },
    {
      "epoch": 0.072992700729927,
      "grad_norm": 0.2586723566055298,
      "learning_rate": 5e-05,
      "loss": 1.3439,
      "step": 5
    },
    {
      "epoch": 0.08759124087591241,
      "grad_norm": 0.263378381729126,
      "learning_rate": 6e-05,
      "loss": 1.3301,
      "step": 6
    },
    {
      "epoch": 0.10218978102189781,
      "grad_norm": 0.3001110553741455,
      "learning_rate": 7e-05,
      "loss": 1.4306,
      "step": 7
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 0.3127408027648926,
      "learning_rate": 8e-05,
      "loss": 1.5269,
      "step": 8
    },
    {
      "epoch": 0.13138686131386862,
      "grad_norm": 0.3306756913661957,
      "learning_rate": 9e-05,
      "loss": 1.5575,
      "step": 9
    },
    {
      "epoch": 0.145985401459854,
      "grad_norm": 0.3160371780395508,
      "learning_rate": 0.0001,
      "loss": 1.5351,
      "step": 10
    },
    {
      "epoch": 0.16058394160583941,
      "grad_norm": 0.34496447443962097,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.3777,
      "step": 11
    },
    {
      "epoch": 0.17518248175182483,
      "grad_norm": 0.3498760461807251,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.5107,
      "step": 12
    },
    {
      "epoch": 0.1897810218978102,
      "grad_norm": 0.39934638142585754,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.6022,
      "step": 13
    },
    {
      "epoch": 0.20437956204379562,
      "grad_norm": 0.465092271566391,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.6556,
      "step": 14
    },
    {
      "epoch": 0.21897810218978103,
      "grad_norm": 0.5206804275512695,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.5127,
      "step": 15
    },
    {
      "epoch": 0.23357664233576642,
      "grad_norm": 0.768470048904419,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.5533,
      "step": 16
    },
    {
      "epoch": 0.24817518248175183,
      "grad_norm": 1.090665578842163,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.5642,
      "step": 17
    },
    {
      "epoch": 0.26277372262773724,
      "grad_norm": 0.22523103654384613,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.1164,
      "step": 18
    },
    {
      "epoch": 0.2773722627737226,
      "grad_norm": 0.2752389907836914,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.316,
      "step": 19
    },
    {
      "epoch": 0.291970802919708,
      "grad_norm": 0.3183665871620178,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.4928,
      "step": 20
    },
    {
      "epoch": 0.30656934306569344,
      "grad_norm": 0.27435073256492615,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.4167,
      "step": 21
    },
    {
      "epoch": 0.32116788321167883,
      "grad_norm": 0.2635630965232849,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.3312,
      "step": 22
    },
    {
      "epoch": 0.3357664233576642,
      "grad_norm": 0.283328115940094,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.2401,
      "step": 23
    },
    {
      "epoch": 0.35036496350364965,
      "grad_norm": 0.2754209339618683,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.2968,
      "step": 24
    },
    {
      "epoch": 0.36496350364963503,
      "grad_norm": 0.26876121759414673,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.3258,
      "step": 25
    },
    {
      "epoch": 0.3795620437956204,
      "grad_norm": 0.2775923013687134,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.5213,
      "step": 26
    },
    {
      "epoch": 0.39416058394160586,
      "grad_norm": 0.2922881841659546,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4696,
      "step": 27
    },
    {
      "epoch": 0.40875912408759124,
      "grad_norm": 0.3192733824253082,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.461,
      "step": 28
    },
    {
      "epoch": 0.4233576642335766,
      "grad_norm": 0.30542343854904175,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2845,
      "step": 29
    },
    {
      "epoch": 0.43795620437956206,
      "grad_norm": 0.3349704444408417,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.5112,
      "step": 30
    },
    {
      "epoch": 0.45255474452554745,
      "grad_norm": 0.4194556474685669,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.551,
      "step": 31
    },
    {
      "epoch": 0.46715328467153283,
      "grad_norm": 0.4276324510574341,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.3825,
      "step": 32
    },
    {
      "epoch": 0.48175182481751827,
      "grad_norm": 0.6078927516937256,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2662,
      "step": 33
    },
    {
      "epoch": 0.49635036496350365,
      "grad_norm": 1.161561131477356,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.765,
      "step": 34
    },
    {
      "epoch": 0.5109489051094891,
      "grad_norm": 0.25809964537620544,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.0536,
      "step": 35
    },
    {
      "epoch": 0.5255474452554745,
      "grad_norm": 0.3206067979335785,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.242,
      "step": 36
    },
    {
      "epoch": 0.5401459854014599,
      "grad_norm": 0.3605632185935974,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.392,
      "step": 37
    },
    {
      "epoch": 0.5547445255474452,
      "grad_norm": 0.3188509941101074,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.3066,
      "step": 38
    },
    {
      "epoch": 0.5693430656934306,
      "grad_norm": 0.26123201847076416,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.4529,
      "step": 39
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 0.30387642979621887,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.4268,
      "step": 40
    },
    {
      "epoch": 0.5985401459854015,
      "grad_norm": 0.24363067746162415,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.2571,
      "step": 41
    },
    {
      "epoch": 0.6131386861313869,
      "grad_norm": 0.2345147728919983,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.2949,
      "step": 42
    },
    {
      "epoch": 0.6277372262773723,
      "grad_norm": 0.2796514630317688,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.6697,
      "step": 43
    },
    {
      "epoch": 0.6423357664233577,
      "grad_norm": 0.2493496686220169,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.511,
      "step": 44
    },
    {
      "epoch": 0.656934306569343,
      "grad_norm": 0.2572794258594513,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.549,
      "step": 45
    },
    {
      "epoch": 0.6715328467153284,
      "grad_norm": 0.2896481156349182,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.5029,
      "step": 46
    },
    {
      "epoch": 0.6861313868613139,
      "grad_norm": 0.30924326181411743,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.6589,
      "step": 47
    },
    {
      "epoch": 0.7007299270072993,
      "grad_norm": 0.3268283009529114,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3645,
      "step": 48
    },
    {
      "epoch": 0.7153284671532847,
      "grad_norm": 0.4042142629623413,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.4351,
      "step": 49
    },
    {
      "epoch": 0.7299270072992701,
      "grad_norm": 0.5127891898155212,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.5435,
      "step": 50
    },
    {
      "epoch": 0.7299270072992701,
      "eval_loss": 1.3495919704437256,
      "eval_runtime": 9.5392,
      "eval_samples_per_second": 12.16,
      "eval_steps_per_second": 3.04,
      "step": 50
    },
    {
      "epoch": 0.7445255474452555,
      "grad_norm": 0.8560667634010315,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.8483,
      "step": 51
    },
    {
      "epoch": 0.7591240875912408,
      "grad_norm": 0.19889923930168152,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.2329,
      "step": 52
    },
    {
      "epoch": 0.7737226277372263,
      "grad_norm": 0.1962738186120987,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.1411,
      "step": 53
    },
    {
      "epoch": 0.7883211678832117,
      "grad_norm": 0.26418882608413696,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.2772,
      "step": 54
    },
    {
      "epoch": 0.8029197080291971,
      "grad_norm": 0.24663497507572174,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.3945,
      "step": 55
    },
    {
      "epoch": 0.8175182481751825,
      "grad_norm": 0.2522558271884918,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.3297,
      "step": 56
    },
    {
      "epoch": 0.8321167883211679,
      "grad_norm": 0.23990610241889954,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.2819,
      "step": 57
    },
    {
      "epoch": 0.8467153284671532,
      "grad_norm": 0.24296076595783234,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.3761,
      "step": 58
    },
    {
      "epoch": 0.8613138686131386,
      "grad_norm": 0.3103513717651367,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.5065,
      "step": 59
    },
    {
      "epoch": 0.8759124087591241,
      "grad_norm": 0.30774983763694763,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.5209,
      "step": 60
    },
    {
      "epoch": 0.8905109489051095,
      "grad_norm": 0.28831735253334045,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.3257,
      "step": 61
    },
    {
      "epoch": 0.9051094890510949,
      "grad_norm": 0.29725369811058044,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.3584,
      "step": 62
    },
    {
      "epoch": 0.9197080291970803,
      "grad_norm": 0.3025360405445099,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.4491,
      "step": 63
    },
    {
      "epoch": 0.9343065693430657,
      "grad_norm": 0.33015918731689453,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.617,
      "step": 64
    },
    {
      "epoch": 0.948905109489051,
      "grad_norm": 0.38496652245521545,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.514,
      "step": 65
    },
    {
      "epoch": 0.9635036496350365,
      "grad_norm": 0.4562894105911255,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.4781,
      "step": 66
    },
    {
      "epoch": 0.9781021897810219,
      "grad_norm": 0.6671634316444397,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2929,
      "step": 67
    },
    {
      "epoch": 0.9927007299270073,
      "grad_norm": 0.8460031151771545,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.5043,
      "step": 68
    },
    {
      "epoch": 1.0072992700729928,
      "grad_norm": 0.39379993081092834,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.9251,
      "step": 69
    },
    {
      "epoch": 1.0218978102189782,
      "grad_norm": 0.2024262547492981,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.2559,
      "step": 70
    },
    {
      "epoch": 1.0364963503649636,
      "grad_norm": 0.18454807996749878,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.2004,
      "step": 71
    },
    {
      "epoch": 1.051094890510949,
      "grad_norm": 0.22660477459430695,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.3105,
      "step": 72
    },
    {
      "epoch": 1.0656934306569343,
      "grad_norm": 0.23621201515197754,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.267,
      "step": 73
    },
    {
      "epoch": 1.0802919708029197,
      "grad_norm": 0.21096746623516083,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.224,
      "step": 74
    },
    {
      "epoch": 1.094890510948905,
      "grad_norm": 0.20510925352573395,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.1486,
      "step": 75
    },
    {
      "epoch": 1.1094890510948905,
      "grad_norm": 0.22512950003147125,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.161,
      "step": 76
    },
    {
      "epoch": 1.1240875912408759,
      "grad_norm": 0.24124397337436676,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.3632,
      "step": 77
    },
    {
      "epoch": 1.1386861313868613,
      "grad_norm": 0.2519776225090027,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.474,
      "step": 78
    },
    {
      "epoch": 1.1532846715328466,
      "grad_norm": 0.2746761441230774,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.4399,
      "step": 79
    },
    {
      "epoch": 1.167883211678832,
      "grad_norm": 0.29807841777801514,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.3011,
      "step": 80
    },
    {
      "epoch": 1.1824817518248176,
      "grad_norm": 0.3112080693244934,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.2812,
      "step": 81
    },
    {
      "epoch": 1.197080291970803,
      "grad_norm": 0.37644192576408386,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.5096,
      "step": 82
    },
    {
      "epoch": 1.2116788321167884,
      "grad_norm": 0.407172292470932,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2172,
      "step": 83
    },
    {
      "epoch": 1.2262773722627738,
      "grad_norm": 0.4946073889732361,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.124,
      "step": 84
    },
    {
      "epoch": 1.2408759124087592,
      "grad_norm": 0.6424919366836548,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.0193,
      "step": 85
    },
    {
      "epoch": 1.2554744525547445,
      "grad_norm": 0.5092834830284119,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0477,
      "step": 86
    },
    {
      "epoch": 1.27007299270073,
      "grad_norm": 0.262993186712265,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.1707,
      "step": 87
    },
    {
      "epoch": 1.2846715328467153,
      "grad_norm": 0.33721840381622314,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.3144,
      "step": 88
    },
    {
      "epoch": 1.2992700729927007,
      "grad_norm": 0.29857197403907776,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.2973,
      "step": 89
    },
    {
      "epoch": 1.313868613138686,
      "grad_norm": 0.30272388458251953,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.3957,
      "step": 90
    },
    {
      "epoch": 1.3284671532846715,
      "grad_norm": 0.2774648368358612,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.34,
      "step": 91
    },
    {
      "epoch": 1.343065693430657,
      "grad_norm": 0.2678561508655548,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0816,
      "step": 92
    },
    {
      "epoch": 1.3576642335766422,
      "grad_norm": 0.29622358083724976,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.2971,
      "step": 93
    },
    {
      "epoch": 1.3722627737226278,
      "grad_norm": 0.34723931550979614,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.3993,
      "step": 94
    },
    {
      "epoch": 1.3868613138686132,
      "grad_norm": 0.3615782558917999,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.2986,
      "step": 95
    },
    {
      "epoch": 1.4014598540145986,
      "grad_norm": 0.3415862023830414,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.2167,
      "step": 96
    },
    {
      "epoch": 1.416058394160584,
      "grad_norm": 0.3852068781852722,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.3517,
      "step": 97
    },
    {
      "epoch": 1.4306569343065694,
      "grad_norm": 0.43150535225868225,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.3538,
      "step": 98
    },
    {
      "epoch": 1.4452554744525548,
      "grad_norm": 0.46599894762039185,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.4442,
      "step": 99
    },
    {
      "epoch": 1.4598540145985401,
      "grad_norm": 0.49653562903404236,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.2147,
      "step": 100
    },
    {
      "epoch": 1.4598540145985401,
      "eval_loss": 1.339756965637207,
      "eval_runtime": 9.5296,
      "eval_samples_per_second": 12.173,
      "eval_steps_per_second": 3.043,
      "step": 100
    },
    {
      "epoch": 1.4744525547445255,
      "grad_norm": 0.6112305521965027,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.0104,
      "step": 101
    },
    {
      "epoch": 1.489051094890511,
      "grad_norm": 0.9019709229469299,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.2014,
      "step": 102
    },
    {
      "epoch": 1.5036496350364965,
      "grad_norm": 0.6647908091545105,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9964,
      "step": 103
    },
    {
      "epoch": 1.5182481751824817,
      "grad_norm": 0.2642989158630371,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.1099,
      "step": 104
    },
    {
      "epoch": 1.5328467153284673,
      "grad_norm": 0.39678728580474854,
      "learning_rate": 5e-05,
      "loss": 1.3339,
      "step": 105
    },
    {
      "epoch": 1.5474452554744524,
      "grad_norm": 0.3411710858345032,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.2767,
      "step": 106
    },
    {
      "epoch": 1.562043795620438,
      "grad_norm": 0.3441467583179474,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.2537,
      "step": 107
    },
    {
      "epoch": 1.5766423357664232,
      "grad_norm": 0.3104326128959656,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.2471,
      "step": 108
    },
    {
      "epoch": 1.5912408759124088,
      "grad_norm": 0.3053652346134186,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.2081,
      "step": 109
    },
    {
      "epoch": 1.6058394160583942,
      "grad_norm": 0.28666096925735474,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.1907,
      "step": 110
    },
    {
      "epoch": 1.6204379562043796,
      "grad_norm": 0.31716474890708923,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.3921,
      "step": 111
    },
    {
      "epoch": 1.635036496350365,
      "grad_norm": 0.35377681255340576,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.4728,
      "step": 112
    },
    {
      "epoch": 1.6496350364963503,
      "grad_norm": 0.35280171036720276,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.2392,
      "step": 113
    },
    {
      "epoch": 1.6642335766423357,
      "grad_norm": 0.37958115339279175,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.2817,
      "step": 114
    },
    {
      "epoch": 1.6788321167883211,
      "grad_norm": 0.38889992237091064,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.4648,
      "step": 115
    },
    {
      "epoch": 1.6934306569343067,
      "grad_norm": 0.4462977945804596,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.4402,
      "step": 116
    },
    {
      "epoch": 1.7080291970802919,
      "grad_norm": 0.5330668091773987,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.2604,
      "step": 117
    },
    {
      "epoch": 1.7226277372262775,
      "grad_norm": 0.6323233246803284,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.1433,
      "step": 118
    },
    {
      "epoch": 1.7372262773722627,
      "grad_norm": 0.8020554780960083,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.0921,
      "step": 119
    },
    {
      "epoch": 1.7518248175182483,
      "grad_norm": 0.5067193508148193,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.76,
      "step": 120
    },
    {
      "epoch": 1.7664233576642334,
      "grad_norm": 0.4858672618865967,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.1777,
      "step": 121
    },
    {
      "epoch": 1.781021897810219,
      "grad_norm": 0.3107368052005768,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.2701,
      "step": 122
    },
    {
      "epoch": 1.7956204379562044,
      "grad_norm": 0.32995232939720154,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.3426,
      "step": 123
    },
    {
      "epoch": 1.8102189781021898,
      "grad_norm": 0.3049861490726471,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.2434,
      "step": 124
    },
    {
      "epoch": 1.8248175182481752,
      "grad_norm": 0.2954845130443573,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.1676,
      "step": 125
    },
    {
      "epoch": 1.8394160583941606,
      "grad_norm": 0.29176580905914307,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.217,
      "step": 126
    },
    {
      "epoch": 1.854014598540146,
      "grad_norm": 0.31522488594055176,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.3572,
      "step": 127
    },
    {
      "epoch": 1.8686131386861313,
      "grad_norm": 0.32127049565315247,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.5572,
      "step": 128
    },
    {
      "epoch": 1.883211678832117,
      "grad_norm": 0.3520948588848114,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.4829,
      "step": 129
    },
    {
      "epoch": 1.897810218978102,
      "grad_norm": 0.33745208382606506,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.1593,
      "step": 130
    },
    {
      "epoch": 1.9124087591240877,
      "grad_norm": 0.3643420934677124,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.2546,
      "step": 131
    },
    {
      "epoch": 1.9270072992700729,
      "grad_norm": 0.39143237471580505,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.3228,
      "step": 132
    },
    {
      "epoch": 1.9416058394160585,
      "grad_norm": 0.44887855648994446,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.34,
      "step": 133
    },
    {
      "epoch": 1.9562043795620438,
      "grad_norm": 0.5407630801200867,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.3312,
      "step": 134
    },
    {
      "epoch": 1.9708029197080292,
      "grad_norm": 0.6488416194915771,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.2817,
      "step": 135
    },
    {
      "epoch": 1.9854014598540146,
      "grad_norm": 0.9303044676780701,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.2194,
      "step": 136
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7835693955421448,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.814,
      "step": 137
    },
    {
      "epoch": 2.0145985401459856,
      "grad_norm": 0.29931533336639404,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.0365,
      "step": 138
    },
    {
      "epoch": 2.0291970802919708,
      "grad_norm": 0.25754988193511963,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.2406,
      "step": 139
    },
    {
      "epoch": 2.0437956204379564,
      "grad_norm": 0.26907339692115784,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.3306,
      "step": 140
    },
    {
      "epoch": 2.0583941605839415,
      "grad_norm": 0.28442806005477905,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.24,
      "step": 141
    },
    {
      "epoch": 2.072992700729927,
      "grad_norm": 0.2947362959384918,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.1761,
      "step": 142
    },
    {
      "epoch": 2.0875912408759123,
      "grad_norm": 0.2839207351207733,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.1287,
      "step": 143
    },
    {
      "epoch": 2.102189781021898,
      "grad_norm": 0.300470769405365,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.2139,
      "step": 144
    },
    {
      "epoch": 2.116788321167883,
      "grad_norm": 0.3054853677749634,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.1675,
      "step": 145
    },
    {
      "epoch": 2.1313868613138687,
      "grad_norm": 0.3172527551651001,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.2412,
      "step": 146
    },
    {
      "epoch": 2.145985401459854,
      "grad_norm": 0.3432178497314453,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.2745,
      "step": 147
    },
    {
      "epoch": 2.1605839416058394,
      "grad_norm": 0.34283071756362915,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.0405,
      "step": 148
    },
    {
      "epoch": 2.1751824817518246,
      "grad_norm": 0.4012333154678345,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.3615,
      "step": 149
    },
    {
      "epoch": 2.18978102189781,
      "grad_norm": 0.41470101475715637,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.3054,
      "step": 150
    },
    {
      "epoch": 2.18978102189781,
      "eval_loss": 1.3516054153442383,
      "eval_runtime": 9.7988,
      "eval_samples_per_second": 11.838,
      "eval_steps_per_second": 2.96,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3265653613920256e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}