{
  "best_metric": 1.15530264377594,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.27481964960494676,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013740982480247338,
      "grad_norm": 0.10483797639608383,
      "learning_rate": 1e-05,
      "loss": 0.685,
      "step": 1
    },
    {
      "epoch": 0.0013740982480247338,
      "eval_loss": 3.1940252780914307,
      "eval_runtime": 34.496,
      "eval_samples_per_second": 35.54,
      "eval_steps_per_second": 8.9,
      "step": 1
    },
    {
      "epoch": 0.0027481964960494676,
      "grad_norm": 0.12614668905735016,
      "learning_rate": 2e-05,
      "loss": 0.8576,
      "step": 2
    },
    {
      "epoch": 0.004122294744074201,
      "grad_norm": 0.1203545331954956,
      "learning_rate": 3e-05,
      "loss": 0.8004,
      "step": 3
    },
    {
      "epoch": 0.005496392992098935,
      "grad_norm": 0.15584434568881989,
      "learning_rate": 4e-05,
      "loss": 0.9421,
      "step": 4
    },
    {
      "epoch": 0.006870491240123669,
      "grad_norm": 0.12526264786720276,
      "learning_rate": 5e-05,
      "loss": 0.9097,
      "step": 5
    },
    {
      "epoch": 0.008244589488148402,
      "grad_norm": 0.17115424573421478,
      "learning_rate": 6e-05,
      "loss": 0.853,
      "step": 6
    },
    {
      "epoch": 0.009618687736173137,
      "grad_norm": 0.1487269401550293,
      "learning_rate": 7e-05,
      "loss": 0.9089,
      "step": 7
    },
    {
      "epoch": 0.01099278598419787,
      "grad_norm": 0.16137735545635223,
      "learning_rate": 8e-05,
      "loss": 0.9666,
      "step": 8
    },
    {
      "epoch": 0.012366884232222604,
      "grad_norm": 0.1646752506494522,
      "learning_rate": 9e-05,
      "loss": 0.9473,
      "step": 9
    },
    {
      "epoch": 0.013740982480247337,
      "grad_norm": 0.14249128103256226,
      "learning_rate": 0.0001,
      "loss": 0.9313,
      "step": 10
    },
    {
      "epoch": 0.01511508072827207,
      "grad_norm": 0.14227785170078278,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.0274,
      "step": 11
    },
    {
      "epoch": 0.016489178976296804,
      "grad_norm": 0.13148291409015656,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9655,
      "step": 12
    },
    {
      "epoch": 0.017863277224321537,
      "grad_norm": 0.14134745299816132,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9462,
      "step": 13
    },
    {
      "epoch": 0.019237375472346274,
      "grad_norm": 0.17106777429580688,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.9013,
      "step": 14
    },
    {
      "epoch": 0.020611473720371008,
      "grad_norm": 0.1760517954826355,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1295,
      "step": 15
    },
    {
      "epoch": 0.02198557196839574,
      "grad_norm": 0.18606971204280853,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0306,
      "step": 16
    },
    {
      "epoch": 0.023359670216420474,
      "grad_norm": 0.1609259396791458,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9478,
      "step": 17
    },
    {
      "epoch": 0.024733768464445208,
      "grad_norm": 0.16032931208610535,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9314,
      "step": 18
    },
    {
      "epoch": 0.02610786671246994,
      "grad_norm": 0.15769387781620026,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.958,
      "step": 19
    },
    {
      "epoch": 0.027481964960494674,
      "grad_norm": 0.16979117691516876,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.955,
      "step": 20
    },
    {
      "epoch": 0.028856063208519408,
      "grad_norm": 0.16869910061359406,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.0697,
      "step": 21
    },
    {
      "epoch": 0.03023016145654414,
      "grad_norm": 0.16554862260818481,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.1263,
      "step": 22
    },
    {
      "epoch": 0.03160425970456888,
      "grad_norm": 0.17995749413967133,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.959,
      "step": 23
    },
    {
      "epoch": 0.03297835795259361,
      "grad_norm": 0.17793428897857666,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.0205,
      "step": 24
    },
    {
      "epoch": 0.034352456200618345,
      "grad_norm": 0.19214510917663574,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0424,
      "step": 25
    },
    {
      "epoch": 0.035726554448643075,
      "grad_norm": 0.2098829746246338,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.0954,
      "step": 26
    },
    {
      "epoch": 0.03710065269666781,
      "grad_norm": 0.22864367067813873,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.0736,
      "step": 27
    },
    {
      "epoch": 0.03847475094469255,
      "grad_norm": 0.24899135529994965,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.1175,
      "step": 28
    },
    {
      "epoch": 0.03984884919271728,
      "grad_norm": 0.327673077583313,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2361,
      "step": 29
    },
    {
      "epoch": 0.041222947440742015,
      "grad_norm": 0.2269551157951355,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1343,
      "step": 30
    },
    {
      "epoch": 0.042597045688766745,
      "grad_norm": 0.25991150736808777,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.1223,
      "step": 31
    },
    {
      "epoch": 0.04397114393679148,
      "grad_norm": 0.9044111967086792,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.9592,
      "step": 32
    },
    {
      "epoch": 0.04534524218481621,
      "grad_norm": 4.863947868347168,
      "learning_rate": 9.642770192448536e-05,
      "loss": 6.6147,
      "step": 33
    },
    {
      "epoch": 0.04671934043284095,
      "grad_norm": 9.817158699035645,
      "learning_rate": 9.611448774886924e-05,
      "loss": 10.6669,
      "step": 34
    },
    {
      "epoch": 0.04809343868086568,
      "grad_norm": 10.038134574890137,
      "learning_rate": 9.578866633275288e-05,
      "loss": 9.2908,
      "step": 35
    },
    {
      "epoch": 0.049467536928890415,
      "grad_norm": 8.122660636901855,
      "learning_rate": 9.545032675245813e-05,
      "loss": 7.7528,
      "step": 36
    },
    {
      "epoch": 0.05084163517691515,
      "grad_norm": 8.032499313354492,
      "learning_rate": 9.509956150664796e-05,
      "loss": 7.36,
      "step": 37
    },
    {
      "epoch": 0.05221573342493988,
      "grad_norm": 8.793131828308105,
      "learning_rate": 9.473646649103818e-05,
      "loss": 7.0245,
      "step": 38
    },
    {
      "epoch": 0.05358983167296462,
      "grad_norm": 11.318851470947266,
      "learning_rate": 9.43611409721806e-05,
      "loss": 6.6932,
      "step": 39
    },
    {
      "epoch": 0.05496392992098935,
      "grad_norm": 10.560226440429688,
      "learning_rate": 9.397368756032445e-05,
      "loss": 5.9597,
      "step": 40
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 2.2521822452545166,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.2867,
      "step": 41
    },
    {
      "epoch": 0.057712126417038816,
      "grad_norm": 2.231226682662964,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.4491,
      "step": 42
    },
    {
      "epoch": 0.05908622466506355,
      "grad_norm": 2.6815185546875,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.4901,
      "step": 43
    },
    {
      "epoch": 0.06046032291308828,
      "grad_norm": 2.713806629180908,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.3808,
      "step": 44
    },
    {
      "epoch": 0.06183442116111302,
      "grad_norm": 2.237513303756714,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.4507,
      "step": 45
    },
    {
      "epoch": 0.06320851940913776,
      "grad_norm": 1.633065938949585,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.4302,
      "step": 46
    },
    {
      "epoch": 0.06458261765716249,
      "grad_norm": 1.1060121059417725,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.2984,
      "step": 47
    },
    {
      "epoch": 0.06595671590518722,
      "grad_norm": 0.9864795207977295,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5416,
      "step": 48
    },
    {
      "epoch": 0.06733081415321196,
      "grad_norm": 0.7836622595787048,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.3503,
      "step": 49
    },
    {
      "epoch": 0.06870491240123669,
      "grad_norm": 0.714900553226471,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.5421,
      "step": 50
    },
    {
      "epoch": 0.06870491240123669,
      "eval_loss": 1.5868769884109497,
      "eval_runtime": 34.4314,
      "eval_samples_per_second": 35.607,
      "eval_steps_per_second": 8.916,
      "step": 50
    },
    {
      "epoch": 0.07007901064926142,
      "grad_norm": 0.38415223360061646,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.8299,
      "step": 51
    },
    {
      "epoch": 0.07145310889728615,
      "grad_norm": 0.4247245192527771,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0404,
      "step": 52
    },
    {
      "epoch": 0.0728272071453109,
      "grad_norm": 0.316862016916275,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8729,
      "step": 53
    },
    {
      "epoch": 0.07420130539333562,
      "grad_norm": 0.2595010995864868,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.9665,
      "step": 54
    },
    {
      "epoch": 0.07557540364136035,
      "grad_norm": 0.23392528295516968,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.8241,
      "step": 55
    },
    {
      "epoch": 0.0769495018893851,
      "grad_norm": 0.20148344337940216,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8365,
      "step": 56
    },
    {
      "epoch": 0.07832360013740983,
      "grad_norm": 0.19715772569179535,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9504,
      "step": 57
    },
    {
      "epoch": 0.07969769838543456,
      "grad_norm": 0.15635672211647034,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.9401,
      "step": 58
    },
    {
      "epoch": 0.08107179663345929,
      "grad_norm": 0.14767538011074066,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8955,
      "step": 59
    },
    {
      "epoch": 0.08244589488148403,
      "grad_norm": 0.14495134353637695,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8504,
      "step": 60
    },
    {
      "epoch": 0.08381999312950876,
      "grad_norm": 0.2106609046459198,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.0351,
      "step": 61
    },
    {
      "epoch": 0.08519409137753349,
      "grad_norm": 0.17500390112400055,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.9622,
      "step": 62
    },
    {
      "epoch": 0.08656818962555823,
      "grad_norm": 0.14354266226291656,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.9499,
      "step": 63
    },
    {
      "epoch": 0.08794228787358296,
      "grad_norm": 0.14788341522216797,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8807,
      "step": 64
    },
    {
      "epoch": 0.0893163861216077,
      "grad_norm": 0.14721274375915527,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.9488,
      "step": 65
    },
    {
      "epoch": 0.09069048436963242,
      "grad_norm": 0.15899237990379333,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9382,
      "step": 66
    },
    {
      "epoch": 0.09206458261765717,
      "grad_norm": 0.16308116912841797,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0037,
      "step": 67
    },
    {
      "epoch": 0.0934386808656819,
      "grad_norm": 0.1667751669883728,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9375,
      "step": 68
    },
    {
      "epoch": 0.09481277911370663,
      "grad_norm": 0.15768298506736755,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9522,
      "step": 69
    },
    {
      "epoch": 0.09618687736173136,
      "grad_norm": 0.16992798447608948,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.0563,
      "step": 70
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.17171549797058105,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8753,
      "step": 71
    },
    {
      "epoch": 0.09893507385778083,
      "grad_norm": 0.16158907115459442,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.8616,
      "step": 72
    },
    {
      "epoch": 0.10030917210580556,
      "grad_norm": 0.18144336342811584,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9803,
      "step": 73
    },
    {
      "epoch": 0.1016832703538303,
      "grad_norm": 0.175902858376503,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.8614,
      "step": 74
    },
    {
      "epoch": 0.10305736860185503,
      "grad_norm": 0.172711580991745,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.0328,
      "step": 75
    },
    {
      "epoch": 0.10443146684987976,
      "grad_norm": 0.22507594525814056,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.0608,
      "step": 76
    },
    {
      "epoch": 0.1058055650979045,
      "grad_norm": 0.22698688507080078,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.0897,
      "step": 77
    },
    {
      "epoch": 0.10717966334592924,
      "grad_norm": 0.2237924188375473,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.1392,
      "step": 78
    },
    {
      "epoch": 0.10855376159395397,
      "grad_norm": 0.25293752551078796,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.1523,
      "step": 79
    },
    {
      "epoch": 0.1099278598419787,
      "grad_norm": 0.25023573637008667,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.0528,
      "step": 80
    },
    {
      "epoch": 0.11130195809000344,
      "grad_norm": 0.4677727222442627,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.3914,
      "step": 81
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 2.5116567611694336,
      "learning_rate": 6.855986244591104e-05,
      "loss": 4.4535,
      "step": 82
    },
    {
      "epoch": 0.1140501545860529,
      "grad_norm": 1.9132788181304932,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.6964,
      "step": 83
    },
    {
      "epoch": 0.11542425283407763,
      "grad_norm": 8.545825958251953,
      "learning_rate": 6.701465872208216e-05,
      "loss": 5.4946,
      "step": 84
    },
    {
      "epoch": 0.11679835108210238,
      "grad_norm": 8.154637336730957,
      "learning_rate": 6.623497346023418e-05,
      "loss": 5.6821,
      "step": 85
    },
    {
      "epoch": 0.1181724493301271,
      "grad_norm": 7.85538911819458,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.3585,
      "step": 86
    },
    {
      "epoch": 0.11954654757815183,
      "grad_norm": 6.4741902351379395,
      "learning_rate": 6.466250186922325e-05,
      "loss": 4.2189,
      "step": 87
    },
    {
      "epoch": 0.12092064582617656,
      "grad_norm": 6.295192241668701,
      "learning_rate": 6.387014543809223e-05,
      "loss": 4.7169,
      "step": 88
    },
    {
      "epoch": 0.12229474407420131,
      "grad_norm": 5.603629112243652,
      "learning_rate": 6.307399704769099e-05,
      "loss": 3.796,
      "step": 89
    },
    {
      "epoch": 0.12366884232222604,
      "grad_norm": 4.813391208648682,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.0979,
      "step": 90
    },
    {
      "epoch": 0.12504294057025078,
      "grad_norm": 0.38076451420783997,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.1222,
      "step": 91
    },
    {
      "epoch": 0.1264170388182755,
      "grad_norm": 0.3639879524707794,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.8106,
      "step": 92
    },
    {
      "epoch": 0.12779113706630024,
      "grad_norm": 0.3948654532432556,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.9167,
      "step": 93
    },
    {
      "epoch": 0.12916523531432497,
      "grad_norm": 0.4553993344306946,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.8786,
      "step": 94
    },
    {
      "epoch": 0.1305393335623497,
      "grad_norm": 0.5135149359703064,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.3219,
      "step": 95
    },
    {
      "epoch": 0.13191343181037443,
      "grad_norm": 0.539106011390686,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.3458,
      "step": 96
    },
    {
      "epoch": 0.13328753005839916,
      "grad_norm": 0.49190863966941833,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.0833,
      "step": 97
    },
    {
      "epoch": 0.13466162830642392,
      "grad_norm": 0.5033016800880432,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.1504,
      "step": 98
    },
    {
      "epoch": 0.13603572655444865,
      "grad_norm": 0.5066355466842651,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.2441,
      "step": 99
    },
    {
      "epoch": 0.13740982480247338,
      "grad_norm": 0.5491134524345398,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.5701,
      "step": 100
    },
    {
      "epoch": 0.13740982480247338,
      "eval_loss": 1.232641577720642,
      "eval_runtime": 34.4034,
      "eval_samples_per_second": 35.636,
      "eval_steps_per_second": 8.924,
      "step": 100
    },
    {
      "epoch": 0.1387839230504981,
      "grad_norm": 0.22732499241828918,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7784,
      "step": 101
    },
    {
      "epoch": 0.14015802129852284,
      "grad_norm": 0.24090968072414398,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8347,
      "step": 102
    },
    {
      "epoch": 0.14153211954654757,
      "grad_norm": 0.27025172114372253,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9203,
      "step": 103
    },
    {
      "epoch": 0.1429062177945723,
      "grad_norm": 0.23090600967407227,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8196,
      "step": 104
    },
    {
      "epoch": 0.14428031604259706,
      "grad_norm": 0.23836828768253326,
      "learning_rate": 5e-05,
      "loss": 0.881,
      "step": 105
    },
    {
      "epoch": 0.1456544142906218,
      "grad_norm": 0.2320927083492279,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9065,
      "step": 106
    },
    {
      "epoch": 0.14702851253864652,
      "grad_norm": 0.19702297449111938,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.8499,
      "step": 107
    },
    {
      "epoch": 0.14840261078667125,
      "grad_norm": 0.26639115810394287,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.8657,
      "step": 108
    },
    {
      "epoch": 0.14977670903469598,
      "grad_norm": 0.1769983321428299,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8158,
      "step": 109
    },
    {
      "epoch": 0.1511508072827207,
      "grad_norm": 0.19121268391609192,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8166,
      "step": 110
    },
    {
      "epoch": 0.15252490553074544,
      "grad_norm": 0.19311772286891937,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8936,
      "step": 111
    },
    {
      "epoch": 0.1538990037787702,
      "grad_norm": 0.21501722931861877,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.9982,
      "step": 112
    },
    {
      "epoch": 0.15527310202679492,
      "grad_norm": 0.15623266994953156,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.8828,
      "step": 113
    },
    {
      "epoch": 0.15664720027481965,
      "grad_norm": 0.18465669453144073,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.9042,
      "step": 114
    },
    {
      "epoch": 0.15802129852284438,
      "grad_norm": 0.1813853681087494,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.9196,
      "step": 115
    },
    {
      "epoch": 0.1593953967708691,
      "grad_norm": 0.16580604016780853,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.9039,
      "step": 116
    },
    {
      "epoch": 0.16076949501889384,
      "grad_norm": 0.16170097887516022,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8771,
      "step": 117
    },
    {
      "epoch": 0.16214359326691857,
      "grad_norm": 0.1513260155916214,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9403,
      "step": 118
    },
    {
      "epoch": 0.16351769151494333,
      "grad_norm": 0.16080285608768463,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.9098,
      "step": 119
    },
    {
      "epoch": 0.16489178976296806,
      "grad_norm": 0.20174327492713928,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.838,
      "step": 120
    },
    {
      "epoch": 0.1662658880109928,
      "grad_norm": 0.16623294353485107,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.9913,
      "step": 121
    },
    {
      "epoch": 0.16763998625901752,
      "grad_norm": 0.16059638559818268,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.8906,
      "step": 122
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 0.15842345356941223,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.9219,
      "step": 123
    },
    {
      "epoch": 0.17038818275506698,
      "grad_norm": 0.1533871442079544,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8807,
      "step": 124
    },
    {
      "epoch": 0.1717622810030917,
      "grad_norm": 0.19062799215316772,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.0445,
      "step": 125
    },
    {
      "epoch": 0.17313637925111647,
      "grad_norm": 0.18164344131946564,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.0127,
      "step": 126
    },
    {
      "epoch": 0.1745104774991412,
      "grad_norm": 0.19414466619491577,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.0392,
      "step": 127
    },
    {
      "epoch": 0.17588457574716593,
      "grad_norm": 0.20451973378658295,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.0717,
      "step": 128
    },
    {
      "epoch": 0.17725867399519066,
      "grad_norm": 0.2361365258693695,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.077,
      "step": 129
    },
    {
      "epoch": 0.1786327722432154,
      "grad_norm": 0.22108298540115356,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.0814,
      "step": 130
    },
    {
      "epoch": 0.18000687049124012,
      "grad_norm": 0.2943987250328064,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.3099,
      "step": 131
    },
    {
      "epoch": 0.18138096873926485,
      "grad_norm": 0.262597918510437,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.1206,
      "step": 132
    },
    {
      "epoch": 0.1827550669872896,
      "grad_norm": 0.20935556292533875,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.808,
      "step": 133
    },
    {
      "epoch": 0.18412916523531433,
      "grad_norm": 1.6019654273986816,
      "learning_rate": 2.693294185106562e-05,
      "loss": 3.173,
      "step": 134
    },
    {
      "epoch": 0.18550326348333906,
      "grad_norm": 1.4684656858444214,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.7794,
      "step": 135
    },
    {
      "epoch": 0.1868773617313638,
      "grad_norm": 4.074985027313232,
      "learning_rate": 2.547882480847461e-05,
      "loss": 2.8301,
      "step": 136
    },
    {
      "epoch": 0.18825145997938852,
      "grad_norm": 3.803900718688965,
      "learning_rate": 2.476172311325783e-05,
      "loss": 2.404,
      "step": 137
    },
    {
      "epoch": 0.18962555822741325,
      "grad_norm": 0.9585076570510864,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7793,
      "step": 138
    },
    {
      "epoch": 0.19099965647543798,
      "grad_norm": 0.9903165102005005,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.6105,
      "step": 139
    },
    {
      "epoch": 0.19237375472346271,
      "grad_norm": 3.821521759033203,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.5815,
      "step": 140
    },
    {
      "epoch": 0.19374785297148747,
      "grad_norm": 3.627880096435547,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.1078,
      "step": 141
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.4024462401866913,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.0797,
      "step": 142
    },
    {
      "epoch": 0.19649604946753693,
      "grad_norm": 0.29357773065567017,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8633,
      "step": 143
    },
    {
      "epoch": 0.19787014771556166,
      "grad_norm": 0.34550121426582336,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.1603,
      "step": 144
    },
    {
      "epoch": 0.1992442459635864,
      "grad_norm": 0.2187006175518036,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.798,
      "step": 145
    },
    {
      "epoch": 0.20061834421161112,
      "grad_norm": 0.28694215416908264,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.896,
      "step": 146
    },
    {
      "epoch": 0.20199244245963585,
      "grad_norm": 0.26941293478012085,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.8048,
      "step": 147
    },
    {
      "epoch": 0.2033665407076606,
      "grad_norm": 0.333441823720932,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.2131,
      "step": 148
    },
    {
      "epoch": 0.20474063895568534,
      "grad_norm": 0.2976028323173523,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.0769,
      "step": 149
    },
    {
      "epoch": 0.20611473720371007,
      "grad_norm": 0.3701110780239105,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.3216,
      "step": 150
    },
    {
      "epoch": 0.20611473720371007,
      "eval_loss": 1.1635231971740723,
      "eval_runtime": 34.4009,
      "eval_samples_per_second": 35.639,
      "eval_steps_per_second": 8.924,
      "step": 150
    },
    {
      "epoch": 0.2074888354517348,
      "grad_norm": 0.16084638237953186,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.8135,
      "step": 151
    },
    {
      "epoch": 0.20886293369975953,
      "grad_norm": 0.1369766741991043,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.748,
      "step": 152
    },
    {
      "epoch": 0.21023703194778426,
      "grad_norm": 0.16258276998996735,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.9021,
      "step": 153
    },
    {
      "epoch": 0.211611130195809,
      "grad_norm": 0.15553633868694305,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.8647,
      "step": 154
    },
    {
      "epoch": 0.21298522844383375,
      "grad_norm": 0.14058363437652588,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7812,
      "step": 155
    },
    {
      "epoch": 0.21435932669185848,
      "grad_norm": 0.1647876501083374,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.8612,
      "step": 156
    },
    {
      "epoch": 0.2157334249398832,
      "grad_norm": 0.13464131951332092,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.8543,
      "step": 157
    },
    {
      "epoch": 0.21710752318790794,
      "grad_norm": 0.1704424023628235,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.9395,
      "step": 158
    },
    {
      "epoch": 0.21848162143593267,
      "grad_norm": 0.17699450254440308,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8878,
      "step": 159
    },
    {
      "epoch": 0.2198557196839574,
      "grad_norm": 0.1722426861524582,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.9037,
      "step": 160
    },
    {
      "epoch": 0.22122981793198213,
      "grad_norm": 0.15306656062602997,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.8459,
      "step": 161
    },
    {
      "epoch": 0.22260391618000688,
      "grad_norm": 0.16906309127807617,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9504,
      "step": 162
    },
    {
      "epoch": 0.2239780144280316,
      "grad_norm": 0.15309089422225952,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.9104,
      "step": 163
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 0.15474851429462433,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.8463,
      "step": 164
    },
    {
      "epoch": 0.22672621092408107,
      "grad_norm": 0.17299772799015045,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.9813,
      "step": 165
    },
    {
      "epoch": 0.2281003091721058,
      "grad_norm": 0.1648123860359192,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.916,
      "step": 166
    },
    {
      "epoch": 0.22947440742013053,
      "grad_norm": 0.17733259499073029,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.0384,
      "step": 167
    },
    {
      "epoch": 0.23084850566815526,
      "grad_norm": 0.16856180131435394,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.9116,
      "step": 168
    },
    {
      "epoch": 0.23222260391618002,
      "grad_norm": 0.15568293631076813,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8829,
      "step": 169
    },
    {
      "epoch": 0.23359670216420475,
      "grad_norm": 0.18964214622974396,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.0114,
      "step": 170
    },
    {
      "epoch": 0.23497080041222948,
      "grad_norm": 0.1761711686849594,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.9506,
      "step": 171
    },
    {
      "epoch": 0.2363448986602542,
      "grad_norm": 0.18085990846157074,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.9117,
      "step": 172
    },
    {
      "epoch": 0.23771899690827894,
      "grad_norm": 0.16631512343883514,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.865,
      "step": 173
    },
    {
      "epoch": 0.23909309515630367,
      "grad_norm": 0.17146159708499908,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.9085,
      "step": 174
    },
    {
      "epoch": 0.2404671934043284,
      "grad_norm": 0.18984918296337128,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.9626,
      "step": 175
    },
    {
      "epoch": 0.24184129165235313,
      "grad_norm": 0.20540012419223785,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.998,
      "step": 176
    },
    {
      "epoch": 0.2432153899003779,
      "grad_norm": 0.18267303705215454,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.977,
      "step": 177
    },
    {
      "epoch": 0.24458948814840262,
      "grad_norm": 0.20427419245243073,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.9438,
      "step": 178
    },
    {
      "epoch": 0.24596358639642735,
      "grad_norm": 0.2463366687297821,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.0189,
      "step": 179
    },
    {
      "epoch": 0.24733768464445208,
      "grad_norm": 0.3353798985481262,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.4197,
      "step": 180
    },
    {
      "epoch": 0.2487117828924768,
      "grad_norm": 0.2744928300380707,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.9005,
      "step": 181
    },
    {
      "epoch": 0.25008588114050156,
      "grad_norm": 1.388237714767456,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 2.5154,
      "step": 182
    },
    {
      "epoch": 0.25145997938852627,
      "grad_norm": 0.3772825002670288,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.0207,
      "step": 183
    },
    {
      "epoch": 0.252834077636551,
      "grad_norm": 3.298708915710449,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 2.0159,
      "step": 184
    },
    {
      "epoch": 0.2542081758845757,
      "grad_norm": 3.4532456398010254,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.9824,
      "step": 185
    },
    {
      "epoch": 0.2555822741326005,
      "grad_norm": 3.551166296005249,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.7568,
      "step": 186
    },
    {
      "epoch": 0.25695637238062524,
      "grad_norm": 2.756852626800537,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.8877,
      "step": 187
    },
    {
      "epoch": 0.25833047062864994,
      "grad_norm": 3.3876028060913086,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.6907,
      "step": 188
    },
    {
      "epoch": 0.2597045688766747,
      "grad_norm": 0.6075344681739807,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8937,
      "step": 189
    },
    {
      "epoch": 0.2610786671246994,
      "grad_norm": 3.48028302192688,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.9191,
      "step": 190
    },
    {
      "epoch": 0.26245276537272416,
      "grad_norm": 0.7353936433792114,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.9656,
      "step": 191
    },
    {
      "epoch": 0.26382686362074886,
      "grad_norm": 0.24418112635612488,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.8601,
      "step": 192
    },
    {
      "epoch": 0.2652009618687736,
      "grad_norm": 0.2983400225639343,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.8761,
      "step": 193
    },
    {
      "epoch": 0.2665750601167983,
      "grad_norm": 0.27170583605766296,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.8213,
      "step": 194
    },
    {
      "epoch": 0.2679491583648231,
      "grad_norm": 0.2670496106147766,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.9032,
      "step": 195
    },
    {
      "epoch": 0.26932325661284784,
      "grad_norm": 0.2921360433101654,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.0317,
      "step": 196
    },
    {
      "epoch": 0.27069735486087254,
      "grad_norm": 0.23456686735153198,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.8956,
      "step": 197
    },
    {
      "epoch": 0.2720714531088973,
      "grad_norm": 0.27625733613967896,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.8778,
      "step": 198
    },
    {
      "epoch": 0.273445551356922,
      "grad_norm": 0.288483589887619,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.1014,
      "step": 199
    },
    {
      "epoch": 0.27481964960494676,
      "grad_norm": 0.47859981656074524,
      "learning_rate": 0.0,
      "loss": 1.4565,
      "step": 200
    },
    {
      "epoch": 0.27481964960494676,
      "eval_loss": 1.15530264377594,
      "eval_runtime": 34.4541,
      "eval_samples_per_second": 35.584,
      "eval_steps_per_second": 8.91,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.500272152641536e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}