{
  "best_metric": 0.36158862709999084,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.06825356198276597,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003412678099138299,
      "grad_norm": 0.18497566878795624,
      "learning_rate": 1e-05,
      "loss": 0.6841,
      "step": 1
    },
    {
      "epoch": 0.0003412678099138299,
      "eval_loss": 0.6862931251525879,
      "eval_runtime": 264.1072,
      "eval_samples_per_second": 74.742,
      "eval_steps_per_second": 4.672,
      "step": 1
    },
    {
      "epoch": 0.0006825356198276597,
      "grad_norm": 0.2475544512271881,
      "learning_rate": 2e-05,
      "loss": 0.7925,
      "step": 2
    },
    {
      "epoch": 0.0010238034297414896,
      "grad_norm": 0.31268638372421265,
      "learning_rate": 3e-05,
      "loss": 0.9425,
      "step": 3
    },
    {
      "epoch": 0.0013650712396553195,
      "grad_norm": 0.3240335285663605,
      "learning_rate": 4e-05,
      "loss": 0.7912,
      "step": 4
    },
    {
      "epoch": 0.0017063390495691494,
      "grad_norm": 0.23378726840019226,
      "learning_rate": 5e-05,
      "loss": 0.5811,
      "step": 5
    },
    {
      "epoch": 0.002047606859482979,
      "grad_norm": 0.22681842744350433,
      "learning_rate": 6e-05,
      "loss": 0.5695,
      "step": 6
    },
    {
      "epoch": 0.0023888746693968093,
      "grad_norm": 0.23531198501586914,
      "learning_rate": 7e-05,
      "loss": 0.5402,
      "step": 7
    },
    {
      "epoch": 0.002730142479310639,
      "grad_norm": 0.23221531510353088,
      "learning_rate": 8e-05,
      "loss": 0.5302,
      "step": 8
    },
    {
      "epoch": 0.0030714102892244687,
      "grad_norm": 0.3206062912940979,
      "learning_rate": 9e-05,
      "loss": 0.5468,
      "step": 9
    },
    {
      "epoch": 0.003412678099138299,
      "grad_norm": 0.3689028322696686,
      "learning_rate": 0.0001,
      "loss": 0.5104,
      "step": 10
    },
    {
      "epoch": 0.0037539459090521286,
      "grad_norm": 0.36002832651138306,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.488,
      "step": 11
    },
    {
      "epoch": 0.004095213718965958,
      "grad_norm": 0.3082902133464813,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.4877,
      "step": 12
    },
    {
      "epoch": 0.004436481528879788,
      "grad_norm": 0.2811516523361206,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.5731,
      "step": 13
    },
    {
      "epoch": 0.0047777493387936186,
      "grad_norm": 0.37978464365005493,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.6767,
      "step": 14
    },
    {
      "epoch": 0.005119017148707448,
      "grad_norm": 0.30328747630119324,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7783,
      "step": 15
    },
    {
      "epoch": 0.005460284958621278,
      "grad_norm": 0.33431947231292725,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.6915,
      "step": 16
    },
    {
      "epoch": 0.005801552768535108,
      "grad_norm": 0.26674115657806396,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.4641,
      "step": 17
    },
    {
      "epoch": 0.006142820578448937,
      "grad_norm": 0.2723121643066406,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.4103,
      "step": 18
    },
    {
      "epoch": 0.006484088388362768,
      "grad_norm": 0.264744371175766,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.4006,
      "step": 19
    },
    {
      "epoch": 0.006825356198276598,
      "grad_norm": 0.2750055193901062,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.3953,
      "step": 20
    },
    {
      "epoch": 0.007166624008190427,
      "grad_norm": 0.28365451097488403,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.3824,
      "step": 21
    },
    {
      "epoch": 0.007507891818104257,
      "grad_norm": 0.2728990912437439,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.3901,
      "step": 22
    },
    {
      "epoch": 0.007849159628018087,
      "grad_norm": 0.27850180864334106,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.3938,
      "step": 23
    },
    {
      "epoch": 0.008190427437931917,
      "grad_norm": 0.28305569291114807,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.3927,
      "step": 24
    },
    {
      "epoch": 0.008531695247845746,
      "grad_norm": 0.32145097851753235,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4059,
      "step": 25
    },
    {
      "epoch": 0.008872963057759576,
      "grad_norm": 0.2383580207824707,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.5451,
      "step": 26
    },
    {
      "epoch": 0.009214230867673407,
      "grad_norm": 0.2614969313144684,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.6252,
      "step": 27
    },
    {
      "epoch": 0.009555498677587237,
      "grad_norm": 0.33322271704673767,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6096,
      "step": 28
    },
    {
      "epoch": 0.009896766487501067,
      "grad_norm": 0.25701799988746643,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4465,
      "step": 29
    },
    {
      "epoch": 0.010238034297414897,
      "grad_norm": 0.2148037850856781,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.3584,
      "step": 30
    },
    {
      "epoch": 0.010579302107328726,
      "grad_norm": 0.22008642554283142,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.405,
      "step": 31
    },
    {
      "epoch": 0.010920569917242556,
      "grad_norm": 0.2444654405117035,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.3618,
      "step": 32
    },
    {
      "epoch": 0.011261837727156386,
      "grad_norm": 0.24904589354991913,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.3611,
      "step": 33
    },
    {
      "epoch": 0.011603105537070215,
      "grad_norm": 0.27627843618392944,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3668,
      "step": 34
    },
    {
      "epoch": 0.011944373346984045,
      "grad_norm": 0.25914326310157776,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3414,
      "step": 35
    },
    {
      "epoch": 0.012285641156897875,
      "grad_norm": 0.25066977739334106,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3579,
      "step": 36
    },
    {
      "epoch": 0.012626908966811706,
      "grad_norm": 0.2889055013656616,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.3759,
      "step": 37
    },
    {
      "epoch": 0.012968176776725536,
      "grad_norm": 0.20416684448719025,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.47,
      "step": 38
    },
    {
      "epoch": 0.013309444586639366,
      "grad_norm": 0.21914133429527283,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.5272,
      "step": 39
    },
    {
      "epoch": 0.013650712396553195,
      "grad_norm": 0.22999605536460876,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.5971,
      "step": 40
    },
    {
      "epoch": 0.013991980206467025,
      "grad_norm": 0.26446372270584106,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6037,
      "step": 41
    },
    {
      "epoch": 0.014333248016380855,
      "grad_norm": 0.23282229900360107,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.3637,
      "step": 42
    },
    {
      "epoch": 0.014674515826294685,
      "grad_norm": 0.21215081214904785,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.3493,
      "step": 43
    },
    {
      "epoch": 0.015015783636208514,
      "grad_norm": 0.21987943351268768,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.338,
      "step": 44
    },
    {
      "epoch": 0.015357051446122344,
      "grad_norm": 0.2044689804315567,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.3274,
      "step": 45
    },
    {
      "epoch": 0.015698319256036174,
      "grad_norm": 0.2244405299425125,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.3531,
      "step": 46
    },
    {
      "epoch": 0.016039587065950003,
      "grad_norm": 0.2271154522895813,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.3351,
      "step": 47
    },
    {
      "epoch": 0.016380854875863833,
      "grad_norm": 0.2316705733537674,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3616,
      "step": 48
    },
    {
      "epoch": 0.016722122685777663,
      "grad_norm": 0.256499320268631,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3317,
      "step": 49
    },
    {
      "epoch": 0.017063390495691493,
      "grad_norm": 0.2996993064880371,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.3743,
      "step": 50
    },
    {
      "epoch": 0.017063390495691493,
      "eval_loss": 0.41175660490989685,
      "eval_runtime": 235.3085,
      "eval_samples_per_second": 83.89,
      "eval_steps_per_second": 5.244,
      "step": 50
    },
    {
      "epoch": 0.017404658305605322,
      "grad_norm": 0.2049894481897354,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4993,
      "step": 51
    },
    {
      "epoch": 0.017745926115519152,
      "grad_norm": 0.21354451775550842,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.5209,
      "step": 52
    },
    {
      "epoch": 0.018087193925432985,
      "grad_norm": 0.24098210036754608,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6135,
      "step": 53
    },
    {
      "epoch": 0.018428461735346815,
      "grad_norm": 0.22961851954460144,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.5341,
      "step": 54
    },
    {
      "epoch": 0.018769729545260645,
      "grad_norm": 0.201799213886261,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.3546,
      "step": 55
    },
    {
      "epoch": 0.019110997355174474,
      "grad_norm": 0.2120453268289566,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.318,
      "step": 56
    },
    {
      "epoch": 0.019452265165088304,
      "grad_norm": 0.20748455822467804,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.319,
      "step": 57
    },
    {
      "epoch": 0.019793532975002134,
      "grad_norm": 0.22522872686386108,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3338,
      "step": 58
    },
    {
      "epoch": 0.020134800784915963,
      "grad_norm": 0.20345957577228546,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.3245,
      "step": 59
    },
    {
      "epoch": 0.020476068594829793,
      "grad_norm": 0.20043089985847473,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.3109,
      "step": 60
    },
    {
      "epoch": 0.020817336404743623,
      "grad_norm": 0.1963178813457489,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.333,
      "step": 61
    },
    {
      "epoch": 0.021158604214657453,
      "grad_norm": 0.24082720279693604,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.3488,
      "step": 62
    },
    {
      "epoch": 0.021499872024571282,
      "grad_norm": 0.21349981427192688,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.4438,
      "step": 63
    },
    {
      "epoch": 0.021841139834485112,
      "grad_norm": 0.22440080344676971,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.5258,
      "step": 64
    },
    {
      "epoch": 0.02218240764439894,
      "grad_norm": 0.22355695068836212,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5843,
      "step": 65
    },
    {
      "epoch": 0.02252367545431277,
      "grad_norm": 0.24970658123493195,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.5235,
      "step": 66
    },
    {
      "epoch": 0.0228649432642266,
      "grad_norm": 0.21168158948421478,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.3448,
      "step": 67
    },
    {
      "epoch": 0.02320621107414043,
      "grad_norm": 0.23335349559783936,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.3174,
      "step": 68
    },
    {
      "epoch": 0.02354747888405426,
      "grad_norm": 0.23679345846176147,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3314,
      "step": 69
    },
    {
      "epoch": 0.02388874669396809,
      "grad_norm": 0.23558004200458527,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.3422,
      "step": 70
    },
    {
      "epoch": 0.02423001450388192,
      "grad_norm": 0.21740683913230896,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.2909,
      "step": 71
    },
    {
      "epoch": 0.02457128231379575,
      "grad_norm": 0.22649434208869934,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.3312,
      "step": 72
    },
    {
      "epoch": 0.024912550123709583,
      "grad_norm": 0.2355552613735199,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.3424,
      "step": 73
    },
    {
      "epoch": 0.025253817933623413,
      "grad_norm": 0.22028999030590057,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.3335,
      "step": 74
    },
    {
      "epoch": 0.025595085743537242,
      "grad_norm": 0.26820605993270874,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.3398,
      "step": 75
    },
    {
      "epoch": 0.025936353553451072,
      "grad_norm": 0.16274772584438324,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.4729,
      "step": 76
    },
    {
      "epoch": 0.0262776213633649,
      "grad_norm": 0.2291819006204605,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.5704,
      "step": 77
    },
    {
      "epoch": 0.02661888917327873,
      "grad_norm": 0.24846778810024261,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.5439,
      "step": 78
    },
    {
      "epoch": 0.02696015698319256,
      "grad_norm": 0.31617650389671326,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.5253,
      "step": 79
    },
    {
      "epoch": 0.02730142479310639,
      "grad_norm": 0.2205945998430252,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.3299,
      "step": 80
    },
    {
      "epoch": 0.02764269260302022,
      "grad_norm": 0.20009973645210266,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3252,
      "step": 81
    },
    {
      "epoch": 0.02798396041293405,
      "grad_norm": 0.21673430502414703,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3123,
      "step": 82
    },
    {
      "epoch": 0.02832522822284788,
      "grad_norm": 0.21185316145420074,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3224,
      "step": 83
    },
    {
      "epoch": 0.02866649603276171,
      "grad_norm": 0.23723237216472626,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.352,
      "step": 84
    },
    {
      "epoch": 0.02900776384267554,
      "grad_norm": 0.2370431125164032,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.308,
      "step": 85
    },
    {
      "epoch": 0.02934903165258937,
      "grad_norm": 0.2488846629858017,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3473,
      "step": 86
    },
    {
      "epoch": 0.0296902994625032,
      "grad_norm": 0.2445327639579773,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3578,
      "step": 87
    },
    {
      "epoch": 0.03003156727241703,
      "grad_norm": 0.18646804988384247,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.4408,
      "step": 88
    },
    {
      "epoch": 0.030372835082330858,
      "grad_norm": 0.21375317871570587,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.4763,
      "step": 89
    },
    {
      "epoch": 0.030714102892244688,
      "grad_norm": 0.23985172808170319,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5524,
      "step": 90
    },
    {
      "epoch": 0.031055370702158518,
      "grad_norm": 0.28279000520706177,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.5787,
      "step": 91
    },
    {
      "epoch": 0.03139663851207235,
      "grad_norm": 0.2413223385810852,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3587,
      "step": 92
    },
    {
      "epoch": 0.03173790632198618,
      "grad_norm": 0.20742368698120117,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.293,
      "step": 93
    },
    {
      "epoch": 0.03207917413190001,
      "grad_norm": 0.2049570530653,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.318,
      "step": 94
    },
    {
      "epoch": 0.032420441941813836,
      "grad_norm": 0.24469810724258423,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.3157,
      "step": 95
    },
    {
      "epoch": 0.032761709751727666,
      "grad_norm": 0.20401744544506073,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3375,
      "step": 96
    },
    {
      "epoch": 0.033102977561641496,
      "grad_norm": 0.22278253734111786,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.2931,
      "step": 97
    },
    {
      "epoch": 0.033444245371555326,
      "grad_norm": 0.2358473837375641,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2938,
      "step": 98
    },
    {
      "epoch": 0.033785513181469155,
      "grad_norm": 0.24663186073303223,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.3375,
      "step": 99
    },
    {
      "epoch": 0.034126780991382985,
      "grad_norm": 0.26277956366539,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.3735,
      "step": 100
    },
    {
      "epoch": 0.034126780991382985,
      "eval_loss": 0.37990063428878784,
      "eval_runtime": 234.965,
      "eval_samples_per_second": 84.012,
      "eval_steps_per_second": 5.252,
      "step": 100
    },
    {
      "epoch": 0.034468048801296815,
      "grad_norm": 0.16129793226718903,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4731,
      "step": 101
    },
    {
      "epoch": 0.034809316611210644,
      "grad_norm": 0.2253504991531372,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5473,
      "step": 102
    },
    {
      "epoch": 0.035150584421124474,
      "grad_norm": 0.2580241858959198,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5201,
      "step": 103
    },
    {
      "epoch": 0.035491852231038304,
      "grad_norm": 0.27417340874671936,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.4761,
      "step": 104
    },
    {
      "epoch": 0.03583312004095214,
      "grad_norm": 0.2158539742231369,
      "learning_rate": 5e-05,
      "loss": 0.3365,
      "step": 105
    },
    {
      "epoch": 0.03617438785086597,
      "grad_norm": 0.2179335206747055,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.3098,
      "step": 106
    },
    {
      "epoch": 0.0365156556607798,
      "grad_norm": 0.2259940207004547,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.2926,
      "step": 107
    },
    {
      "epoch": 0.03685692347069363,
      "grad_norm": 0.2270604819059372,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.323,
      "step": 108
    },
    {
      "epoch": 0.03719819128060746,
      "grad_norm": 0.22030046582221985,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.2834,
      "step": 109
    },
    {
      "epoch": 0.03753945909052129,
      "grad_norm": 0.24005058407783508,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.307,
      "step": 110
    },
    {
      "epoch": 0.03788072690043512,
      "grad_norm": 0.27254408597946167,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.3485,
      "step": 111
    },
    {
      "epoch": 0.03822199471034895,
      "grad_norm": 0.24621416628360748,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.3179,
      "step": 112
    },
    {
      "epoch": 0.03856326252026278,
      "grad_norm": 0.20467038452625275,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.429,
      "step": 113
    },
    {
      "epoch": 0.03890453033017661,
      "grad_norm": 0.24165219068527222,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4942,
      "step": 114
    },
    {
      "epoch": 0.03924579814009044,
      "grad_norm": 0.2582136392593384,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.5515,
      "step": 115
    },
    {
      "epoch": 0.03958706595000427,
      "grad_norm": 0.27229195833206177,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5142,
      "step": 116
    },
    {
      "epoch": 0.0399283337599181,
      "grad_norm": 0.21786056458950043,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.3657,
      "step": 117
    },
    {
      "epoch": 0.04026960156983193,
      "grad_norm": 0.23516137897968292,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.342,
      "step": 118
    },
    {
      "epoch": 0.040610869379745757,
      "grad_norm": 0.20134663581848145,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.3004,
      "step": 119
    },
    {
      "epoch": 0.040952137189659586,
      "grad_norm": 0.2039736956357956,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.2787,
      "step": 120
    },
    {
      "epoch": 0.041293404999573416,
      "grad_norm": 0.22337153553962708,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.3031,
      "step": 121
    },
    {
      "epoch": 0.041634672809487246,
      "grad_norm": 0.21707502007484436,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.2959,
      "step": 122
    },
    {
      "epoch": 0.041975940619401075,
      "grad_norm": 0.23799727857112885,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3139,
      "step": 123
    },
    {
      "epoch": 0.042317208429314905,
      "grad_norm": 0.2188572734594345,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2982,
      "step": 124
    },
    {
      "epoch": 0.042658476239228735,
      "grad_norm": 0.26045840978622437,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.3144,
      "step": 125
    },
    {
      "epoch": 0.042999744049142564,
      "grad_norm": 0.1674930453300476,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.4554,
      "step": 126
    },
    {
      "epoch": 0.043341011859056394,
      "grad_norm": 0.20759105682373047,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.5329,
      "step": 127
    },
    {
      "epoch": 0.043682279668970224,
      "grad_norm": 0.23097668588161469,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5192,
      "step": 128
    },
    {
      "epoch": 0.044023547478884054,
      "grad_norm": 0.2753804922103882,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4202,
      "step": 129
    },
    {
      "epoch": 0.04436481528879788,
      "grad_norm": 0.2095237821340561,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.2953,
      "step": 130
    },
    {
      "epoch": 0.04470608309871171,
      "grad_norm": 0.2132461667060852,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3091,
      "step": 131
    },
    {
      "epoch": 0.04504735090862554,
      "grad_norm": 0.21441613137722015,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.2988,
      "step": 132
    },
    {
      "epoch": 0.04538861871853937,
      "grad_norm": 0.22250419855117798,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.3046,
      "step": 133
    },
    {
      "epoch": 0.0457298865284532,
      "grad_norm": 0.2193128615617752,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.2892,
      "step": 134
    },
    {
      "epoch": 0.04607115433836703,
      "grad_norm": 0.19122985005378723,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2641,
      "step": 135
    },
    {
      "epoch": 0.04641242214828086,
      "grad_norm": 0.2623761296272278,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3437,
      "step": 136
    },
    {
      "epoch": 0.04675368995819469,
      "grad_norm": 0.2327306568622589,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2995,
      "step": 137
    },
    {
      "epoch": 0.04709495776810852,
      "grad_norm": 0.18870247900485992,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.4046,
      "step": 138
    },
    {
      "epoch": 0.04743622557802235,
      "grad_norm": 0.22929644584655762,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.4661,
      "step": 139
    },
    {
      "epoch": 0.04777749338793618,
      "grad_norm": 0.2513699531555176,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.579,
      "step": 140
    },
    {
      "epoch": 0.04811876119785001,
      "grad_norm": 0.24072954058647156,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5762,
      "step": 141
    },
    {
      "epoch": 0.04846002900776384,
      "grad_norm": 0.2634357511997223,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3994,
      "step": 142
    },
    {
      "epoch": 0.04880129681767767,
      "grad_norm": 0.22981932759284973,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2735,
      "step": 143
    },
    {
      "epoch": 0.0491425646275915,
      "grad_norm": 0.22643893957138062,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.2708,
      "step": 144
    },
    {
      "epoch": 0.04948383243750533,
      "grad_norm": 0.23719343543052673,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.3119,
      "step": 145
    },
    {
      "epoch": 0.049825100247419166,
      "grad_norm": 0.22354793548583984,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.2881,
      "step": 146
    },
    {
      "epoch": 0.050166368057332995,
      "grad_norm": 0.23652666807174683,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.3083,
      "step": 147
    },
    {
      "epoch": 0.050507635867246825,
      "grad_norm": 0.22466449439525604,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.313,
      "step": 148
    },
    {
      "epoch": 0.050848903677160655,
      "grad_norm": 0.22616927325725555,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.3104,
      "step": 149
    },
    {
      "epoch": 0.051190171487074485,
      "grad_norm": 0.253631591796875,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3248,
      "step": 150
    },
    {
      "epoch": 0.051190171487074485,
      "eval_loss": 0.36475056409835815,
      "eval_runtime": 234.7864,
      "eval_samples_per_second": 84.076,
      "eval_steps_per_second": 5.256,
      "step": 150
    },
    {
      "epoch": 0.051531439296988314,
      "grad_norm": 0.15865057706832886,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.455,
      "step": 151
    },
    {
      "epoch": 0.051872707106902144,
      "grad_norm": 0.22532756626605988,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.5258,
      "step": 152
    },
    {
      "epoch": 0.052213974916815974,
      "grad_norm": 0.2626725137233734,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5166,
      "step": 153
    },
    {
      "epoch": 0.0525552427267298,
      "grad_norm": 0.24395178258419037,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.3836,
      "step": 154
    },
    {
      "epoch": 0.05289651053664363,
      "grad_norm": 0.23441630601882935,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.3068,
      "step": 155
    },
    {
      "epoch": 0.05323777834655746,
      "grad_norm": 0.23894910514354706,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.3078,
      "step": 156
    },
    {
      "epoch": 0.05357904615647129,
      "grad_norm": 0.24818742275238037,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.2934,
      "step": 157
    },
    {
      "epoch": 0.05392031396638512,
      "grad_norm": 0.22011010348796844,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.2965,
      "step": 158
    },
    {
      "epoch": 0.05426158177629895,
      "grad_norm": 0.252695232629776,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.3232,
      "step": 159
    },
    {
      "epoch": 0.05460284958621278,
      "grad_norm": 0.2296438366174698,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.3051,
      "step": 160
    },
    {
      "epoch": 0.05494411739612661,
      "grad_norm": 0.25187844038009644,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.2965,
      "step": 161
    },
    {
      "epoch": 0.05528538520604044,
      "grad_norm": 0.25570523738861084,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2908,
      "step": 162
    },
    {
      "epoch": 0.05562665301595427,
      "grad_norm": 0.172579824924469,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4087,
      "step": 163
    },
    {
      "epoch": 0.0559679208258681,
      "grad_norm": 0.2092519998550415,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.5145,
      "step": 164
    },
    {
      "epoch": 0.05630918863578193,
      "grad_norm": 0.24386321008205414,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.4698,
      "step": 165
    },
    {
      "epoch": 0.05665045644569576,
      "grad_norm": 0.2736985981464386,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.5834,
      "step": 166
    },
    {
      "epoch": 0.05699172425560959,
      "grad_norm": 0.20719671249389648,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.2898,
      "step": 167
    },
    {
      "epoch": 0.05733299206552342,
      "grad_norm": 0.2177129089832306,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.2897,
      "step": 168
    },
    {
      "epoch": 0.05767425987543725,
      "grad_norm": 0.23331378400325775,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.2952,
      "step": 169
    },
    {
      "epoch": 0.05801552768535108,
      "grad_norm": 0.23656344413757324,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.2812,
      "step": 170
    },
    {
      "epoch": 0.05835679549526491,
      "grad_norm": 0.21916796267032623,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.2885,
      "step": 171
    },
    {
      "epoch": 0.05869806330517874,
      "grad_norm": 0.24757185578346252,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.2599,
      "step": 172
    },
    {
      "epoch": 0.05903933111509257,
      "grad_norm": 0.25519874691963196,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.2992,
      "step": 173
    },
    {
      "epoch": 0.0593805989250064,
      "grad_norm": 0.2511082589626312,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.2692,
      "step": 174
    },
    {
      "epoch": 0.05972186673492023,
      "grad_norm": 0.2942829728126526,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.3367,
      "step": 175
    },
    {
      "epoch": 0.06006313454483406,
      "grad_norm": 0.1710635870695114,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.4499,
      "step": 176
    },
    {
      "epoch": 0.06040440235474789,
      "grad_norm": 0.23996436595916748,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.5191,
      "step": 177
    },
    {
      "epoch": 0.060745670164661716,
      "grad_norm": 0.25386717915534973,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.5579,
      "step": 178
    },
    {
      "epoch": 0.061086937974575546,
      "grad_norm": 0.24131855368614197,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.4305,
      "step": 179
    },
    {
      "epoch": 0.061428205784489376,
      "grad_norm": 0.212690532207489,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.2701,
      "step": 180
    },
    {
      "epoch": 0.061769473594403206,
      "grad_norm": 0.23592545092105865,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3027,
      "step": 181
    },
    {
      "epoch": 0.062110741404317035,
      "grad_norm": 0.21710912883281708,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.3167,
      "step": 182
    },
    {
      "epoch": 0.062452009214230865,
      "grad_norm": 0.21302488446235657,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.2831,
      "step": 183
    },
    {
      "epoch": 0.0627932770241447,
      "grad_norm": 0.2276029735803604,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.2937,
      "step": 184
    },
    {
      "epoch": 0.06313454483405853,
      "grad_norm": 0.2346927374601364,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.2763,
      "step": 185
    },
    {
      "epoch": 0.06347581264397235,
      "grad_norm": 0.248663991689682,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.2816,
      "step": 186
    },
    {
      "epoch": 0.06381708045388619,
      "grad_norm": 0.2640588879585266,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.2996,
      "step": 187
    },
    {
      "epoch": 0.06415834826380001,
      "grad_norm": 0.1743447482585907,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.3895,
      "step": 188
    },
    {
      "epoch": 0.06449961607371385,
      "grad_norm": 0.19019544124603271,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.4746,
      "step": 189
    },
    {
      "epoch": 0.06484088388362767,
      "grad_norm": 0.252658873796463,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.5331,
      "step": 190
    },
    {
      "epoch": 0.06518215169354151,
      "grad_norm": 0.24114876985549927,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.459,
      "step": 191
    },
    {
      "epoch": 0.06552341950345533,
      "grad_norm": 0.2402312159538269,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.3411,
      "step": 192
    },
    {
      "epoch": 0.06586468731336917,
      "grad_norm": 0.22079332172870636,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.2936,
      "step": 193
    },
    {
      "epoch": 0.06620595512328299,
      "grad_norm": 0.23450817167758942,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.3174,
      "step": 194
    },
    {
      "epoch": 0.06654722293319683,
      "grad_norm": 0.2487506866455078,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.2497,
      "step": 195
    },
    {
      "epoch": 0.06688849074311065,
      "grad_norm": 0.2227557897567749,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.3002,
      "step": 196
    },
    {
      "epoch": 0.06722975855302449,
      "grad_norm": 0.2573027014732361,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.3089,
      "step": 197
    },
    {
      "epoch": 0.06757102636293831,
      "grad_norm": 0.25218725204467773,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.3025,
      "step": 198
    },
    {
      "epoch": 0.06791229417285215,
      "grad_norm": 0.25256964564323425,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.3356,
      "step": 199
    },
    {
      "epoch": 0.06825356198276597,
      "grad_norm": 0.27960097789764404,
      "learning_rate": 0.0,
      "loss": 0.3447,
      "step": 200
    },
    {
      "epoch": 0.06825356198276597,
      "eval_loss": 0.36158862709999084,
      "eval_runtime": 234.8413,
      "eval_samples_per_second": 84.057,
      "eval_steps_per_second": 5.255,
      "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": 1.4499077712762634e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}