{
  "best_metric": 1.1569346189498901,
  "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": 0.10449496656656265,
      "learning_rate": 1e-05,
      "loss": 0.685,
      "step": 1
    },
    {
      "epoch": 0.0013740982480247338,
      "eval_loss": 3.1940252780914307,
      "eval_runtime": 34.3377,
      "eval_samples_per_second": 35.704,
      "eval_steps_per_second": 8.941,
      "step": 1
    },
    {
      "epoch": 0.0027481964960494676,
      "grad_norm": 0.12698553502559662,
      "learning_rate": 2e-05,
      "loss": 0.8576,
      "step": 2
    },
    {
      "epoch": 0.004122294744074201,
      "grad_norm": 0.1206165999174118,
      "learning_rate": 3e-05,
      "loss": 0.8005,
      "step": 3
    },
    {
      "epoch": 0.005496392992098935,
      "grad_norm": 0.1564454734325409,
      "learning_rate": 4e-05,
      "loss": 0.9418,
      "step": 4
    },
    {
      "epoch": 0.006870491240123669,
      "grad_norm": 0.1259690225124359,
      "learning_rate": 5e-05,
      "loss": 0.9096,
      "step": 5
    },
    {
      "epoch": 0.008244589488148402,
      "grad_norm": 0.17223022878170013,
      "learning_rate": 6e-05,
      "loss": 0.8532,
      "step": 6
    },
    {
      "epoch": 0.009618687736173137,
      "grad_norm": 0.15041504800319672,
      "learning_rate": 7e-05,
      "loss": 0.9084,
      "step": 7
    },
    {
      "epoch": 0.01099278598419787,
      "grad_norm": 0.16178415715694427,
      "learning_rate": 8e-05,
      "loss": 0.9657,
      "step": 8
    },
    {
      "epoch": 0.012366884232222604,
      "grad_norm": 0.16538500785827637,
      "learning_rate": 9e-05,
      "loss": 0.9476,
      "step": 9
    },
    {
      "epoch": 0.013740982480247337,
      "grad_norm": 0.14299707114696503,
      "learning_rate": 0.0001,
      "loss": 0.9313,
      "step": 10
    },
    {
      "epoch": 0.01511508072827207,
      "grad_norm": 0.14547787606716156,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.028,
      "step": 11
    },
    {
      "epoch": 0.016489178976296804,
      "grad_norm": 0.13256515562534332,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.966,
      "step": 12
    },
    {
      "epoch": 0.017863277224321537,
      "grad_norm": 0.14188960194587708,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9456,
      "step": 13
    },
    {
      "epoch": 0.019237375472346274,
      "grad_norm": 0.17157454788684845,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.9015,
      "step": 14
    },
    {
      "epoch": 0.020611473720371008,
      "grad_norm": 0.1776653230190277,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1293,
      "step": 15
    },
    {
      "epoch": 0.02198557196839574,
      "grad_norm": 0.18649327754974365,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0292,
      "step": 16
    },
    {
      "epoch": 0.023359670216420474,
      "grad_norm": 0.16099286079406738,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9473,
      "step": 17
    },
    {
      "epoch": 0.024733768464445208,
      "grad_norm": 0.16241559386253357,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9326,
      "step": 18
    },
    {
      "epoch": 0.02610786671246994,
      "grad_norm": 0.15960976481437683,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.958,
      "step": 19
    },
    {
      "epoch": 0.027481964960494674,
      "grad_norm": 0.17029209434986115,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.9557,
      "step": 20
    },
    {
      "epoch": 0.028856063208519408,
      "grad_norm": 0.16893550753593445,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.0704,
      "step": 21
    },
    {
      "epoch": 0.03023016145654414,
      "grad_norm": 0.1665865182876587,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.1272,
      "step": 22
    },
    {
      "epoch": 0.03160425970456888,
      "grad_norm": 0.17908026278018951,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.9583,
      "step": 23
    },
    {
      "epoch": 0.03297835795259361,
      "grad_norm": 0.17833438515663147,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.0209,
      "step": 24
    },
    {
      "epoch": 0.034352456200618345,
      "grad_norm": 0.19258497655391693,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0425,
      "step": 25
    },
    {
      "epoch": 0.035726554448643075,
      "grad_norm": 0.2108372449874878,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.0958,
      "step": 26
    },
    {
      "epoch": 0.03710065269666781,
      "grad_norm": 0.22890976071357727,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.0739,
      "step": 27
    },
    {
      "epoch": 0.03847475094469255,
      "grad_norm": 0.2488207370042801,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.1178,
      "step": 28
    },
    {
      "epoch": 0.03984884919271728,
      "grad_norm": 0.34948021173477173,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2379,
      "step": 29
    },
    {
      "epoch": 0.041222947440742015,
      "grad_norm": 0.2291388362646103,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1342,
      "step": 30
    },
    {
      "epoch": 0.042597045688766745,
      "grad_norm": 0.2601719796657562,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.1234,
      "step": 31
    },
    {
      "epoch": 0.04397114393679148,
      "grad_norm": 0.9040616750717163,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.961,
      "step": 32
    },
    {
      "epoch": 0.04534524218481621,
      "grad_norm": 4.889550685882568,
      "learning_rate": 9.642770192448536e-05,
      "loss": 6.5999,
      "step": 33
    },
    {
      "epoch": 0.04671934043284095,
      "grad_norm": 9.887581825256348,
      "learning_rate": 9.611448774886924e-05,
      "loss": 10.6638,
      "step": 34
    },
    {
      "epoch": 0.04809343868086568,
      "grad_norm": 10.088833808898926,
      "learning_rate": 9.578866633275288e-05,
      "loss": 9.3249,
      "step": 35
    },
    {
      "epoch": 0.049467536928890415,
      "grad_norm": 8.188547134399414,
      "learning_rate": 9.545032675245813e-05,
      "loss": 7.7799,
      "step": 36
    },
    {
      "epoch": 0.05084163517691515,
      "grad_norm": 8.082768440246582,
      "learning_rate": 9.509956150664796e-05,
      "loss": 7.3824,
      "step": 37
    },
    {
      "epoch": 0.05221573342493988,
      "grad_norm": 8.77908992767334,
      "learning_rate": 9.473646649103818e-05,
      "loss": 7.0547,
      "step": 38
    },
    {
      "epoch": 0.05358983167296462,
      "grad_norm": 11.277396202087402,
      "learning_rate": 9.43611409721806e-05,
      "loss": 6.6999,
      "step": 39
    },
    {
      "epoch": 0.05496392992098935,
      "grad_norm": 10.551315307617188,
      "learning_rate": 9.397368756032445e-05,
      "loss": 5.9977,
      "step": 40
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 2.259110927581787,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.3141,
      "step": 41
    },
    {
      "epoch": 0.057712126417038816,
      "grad_norm": 2.2921853065490723,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.4533,
      "step": 42
    },
    {
      "epoch": 0.05908622466506355,
      "grad_norm": 2.7193686962127686,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.4905,
      "step": 43
    },
    {
      "epoch": 0.06046032291308828,
      "grad_norm": 2.762061595916748,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.3793,
      "step": 44
    },
    {
      "epoch": 0.06183442116111302,
      "grad_norm": 2.2624876499176025,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.451,
      "step": 45
    },
    {
      "epoch": 0.06320851940913776,
      "grad_norm": 1.6451109647750854,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.4289,
      "step": 46
    },
    {
      "epoch": 0.06458261765716249,
      "grad_norm": 1.1050125360488892,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.2959,
      "step": 47
    },
    {
      "epoch": 0.06595671590518722,
      "grad_norm": 0.9729636907577515,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5379,
      "step": 48
    },
    {
      "epoch": 0.06733081415321196,
      "grad_norm": 0.7741087079048157,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.3483,
      "step": 49
    },
    {
      "epoch": 0.06870491240123669,
      "grad_norm": 0.7006238102912903,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.5405,
      "step": 50
    },
    {
      "epoch": 0.06870491240123669,
      "eval_loss": 1.5879584550857544,
      "eval_runtime": 34.2435,
      "eval_samples_per_second": 35.802,
      "eval_steps_per_second": 8.965,
      "step": 50
    },
    {
      "epoch": 0.07007901064926142,
      "grad_norm": 0.36951956152915955,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.8266,
      "step": 51
    },
    {
      "epoch": 0.07145310889728615,
      "grad_norm": 0.4150029718875885,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0378,
      "step": 52
    },
    {
      "epoch": 0.0728272071453109,
      "grad_norm": 0.3108726441860199,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8718,
      "step": 53
    },
    {
      "epoch": 0.07420130539333562,
      "grad_norm": 0.25595834851264954,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.9661,
      "step": 54
    },
    {
      "epoch": 0.07557540364136035,
      "grad_norm": 0.23237261176109314,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.8244,
      "step": 55
    },
    {
      "epoch": 0.0769495018893851,
      "grad_norm": 0.2012605220079422,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8368,
      "step": 56
    },
    {
      "epoch": 0.07832360013740983,
      "grad_norm": 0.19685639441013336,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9504,
      "step": 57
    },
    {
      "epoch": 0.07969769838543456,
      "grad_norm": 0.15504111349582672,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.9402,
      "step": 58
    },
    {
      "epoch": 0.08107179663345929,
      "grad_norm": 0.14742429554462433,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8961,
      "step": 59
    },
    {
      "epoch": 0.08244589488148403,
      "grad_norm": 0.14479437470436096,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8511,
      "step": 60
    },
    {
      "epoch": 0.08381999312950876,
      "grad_norm": 0.21303322911262512,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.0357,
      "step": 61
    },
    {
      "epoch": 0.08519409137753349,
      "grad_norm": 0.17522941529750824,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.9622,
      "step": 62
    },
    {
      "epoch": 0.08656818962555823,
      "grad_norm": 0.14391349256038666,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.9494,
      "step": 63
    },
    {
      "epoch": 0.08794228787358296,
      "grad_norm": 0.14656062424182892,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8806,
      "step": 64
    },
    {
      "epoch": 0.0893163861216077,
      "grad_norm": 0.14807440340518951,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.9496,
      "step": 65
    },
    {
      "epoch": 0.09069048436963242,
      "grad_norm": 0.15757878124713898,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9381,
      "step": 66
    },
    {
      "epoch": 0.09206458261765717,
      "grad_norm": 0.16349080204963684,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0036,
      "step": 67
    },
    {
      "epoch": 0.0934386808656819,
      "grad_norm": 0.16634200513362885,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9379,
      "step": 68
    },
    {
      "epoch": 0.09481277911370663,
      "grad_norm": 0.15692797303199768,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9527,
      "step": 69
    },
    {
      "epoch": 0.09618687736173136,
      "grad_norm": 0.17008203268051147,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.0556,
      "step": 70
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.17098601162433624,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8759,
      "step": 71
    },
    {
      "epoch": 0.09893507385778083,
      "grad_norm": 0.16078433394432068,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.8621,
      "step": 72
    },
    {
      "epoch": 0.10030917210580556,
      "grad_norm": 0.18145760893821716,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9789,
      "step": 73
    },
    {
      "epoch": 0.1016832703538303,
      "grad_norm": 0.17817752063274384,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.862,
      "step": 74
    },
    {
      "epoch": 0.10305736860185503,
      "grad_norm": 0.17206218838691711,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.0341,
      "step": 75
    },
    {
      "epoch": 0.10443146684987976,
      "grad_norm": 0.2242055982351303,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.0616,
      "step": 76
    },
    {
      "epoch": 0.1058055650979045,
      "grad_norm": 0.22674217820167542,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.0889,
      "step": 77
    },
    {
      "epoch": 0.10717966334592924,
      "grad_norm": 0.22443896532058716,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.1406,
      "step": 78
    },
    {
      "epoch": 0.10855376159395397,
      "grad_norm": 0.2545221447944641,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.1522,
      "step": 79
    },
    {
      "epoch": 0.1099278598419787,
      "grad_norm": 0.2507588863372803,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.054,
      "step": 80
    },
    {
      "epoch": 0.11130195809000344,
      "grad_norm": 0.4739324152469635,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.3922,
      "step": 81
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 2.4948577880859375,
      "learning_rate": 6.855986244591104e-05,
      "loss": 4.44,
      "step": 82
    },
    {
      "epoch": 0.1140501545860529,
      "grad_norm": 1.8920295238494873,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.6874,
      "step": 83
    },
    {
      "epoch": 0.11542425283407763,
      "grad_norm": 8.50973892211914,
      "learning_rate": 6.701465872208216e-05,
      "loss": 5.4896,
      "step": 84
    },
    {
      "epoch": 0.11679835108210238,
      "grad_norm": 8.19951343536377,
      "learning_rate": 6.623497346023418e-05,
      "loss": 5.6956,
      "step": 85
    },
    {
      "epoch": 0.1181724493301271,
      "grad_norm": 7.9064178466796875,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.3459,
      "step": 86
    },
    {
      "epoch": 0.11954654757815183,
      "grad_norm": 6.5203680992126465,
      "learning_rate": 6.466250186922325e-05,
      "loss": 4.2154,
      "step": 87
    },
    {
      "epoch": 0.12092064582617656,
      "grad_norm": 6.333930969238281,
      "learning_rate": 6.387014543809223e-05,
      "loss": 4.7078,
      "step": 88
    },
    {
      "epoch": 0.12229474407420131,
      "grad_norm": 5.560692310333252,
      "learning_rate": 6.307399704769099e-05,
      "loss": 3.8004,
      "step": 89
    },
    {
      "epoch": 0.12366884232222604,
      "grad_norm": 4.807435035705566,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.0927,
      "step": 90
    },
    {
      "epoch": 0.12504294057025078,
      "grad_norm": 0.3844199478626251,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.1214,
      "step": 91
    },
    {
      "epoch": 0.1264170388182755,
      "grad_norm": 0.3641394376754761,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.8109,
      "step": 92
    },
    {
      "epoch": 0.12779113706630024,
      "grad_norm": 0.397225946187973,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.9182,
      "step": 93
    },
    {
      "epoch": 0.12916523531432497,
      "grad_norm": 0.47473955154418945,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.8806,
      "step": 94
    },
    {
      "epoch": 0.1305393335623497,
      "grad_norm": 0.5178055167198181,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.3221,
      "step": 95
    },
    {
      "epoch": 0.13191343181037443,
      "grad_norm": 0.5333870649337769,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.346,
      "step": 96
    },
    {
      "epoch": 0.13328753005839916,
      "grad_norm": 0.4927959442138672,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.0839,
      "step": 97
    },
    {
      "epoch": 0.13466162830642392,
      "grad_norm": 0.5075790882110596,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.1515,
      "step": 98
    },
    {
      "epoch": 0.13603572655444865,
      "grad_norm": 0.5081772208213806,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.2446,
      "step": 99
    },
    {
      "epoch": 0.13740982480247338,
      "grad_norm": 0.547201931476593,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.5702,
      "step": 100
    },
    {
      "epoch": 0.13740982480247338,
      "eval_loss": 1.2334567308425903,
      "eval_runtime": 34.2218,
      "eval_samples_per_second": 35.825,
      "eval_steps_per_second": 8.971,
      "step": 100
    },
    {
      "epoch": 0.1387839230504981,
      "grad_norm": 0.2240952104330063,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7776,
      "step": 101
    },
    {
      "epoch": 0.14015802129852284,
      "grad_norm": 0.23646415770053864,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8334,
      "step": 102
    },
    {
      "epoch": 0.14153211954654757,
      "grad_norm": 0.26775121688842773,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9193,
      "step": 103
    },
    {
      "epoch": 0.1429062177945723,
      "grad_norm": 0.22889456152915955,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8188,
      "step": 104
    },
    {
      "epoch": 0.14428031604259706,
      "grad_norm": 0.2366335242986679,
      "learning_rate": 5e-05,
      "loss": 0.8804,
      "step": 105
    },
    {
      "epoch": 0.1456544142906218,
      "grad_norm": 0.23138950765132904,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9062,
      "step": 106
    },
    {
      "epoch": 0.14702851253864652,
      "grad_norm": 0.19622281193733215,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.8498,
      "step": 107
    },
    {
      "epoch": 0.14840261078667125,
      "grad_norm": 0.2636115252971649,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.8661,
      "step": 108
    },
    {
      "epoch": 0.14977670903469598,
      "grad_norm": 0.1766984611749649,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8156,
      "step": 109
    },
    {
      "epoch": 0.1511508072827207,
      "grad_norm": 0.19132503867149353,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8168,
      "step": 110
    },
    {
      "epoch": 0.15252490553074544,
      "grad_norm": 0.19168604910373688,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8933,
      "step": 111
    },
    {
      "epoch": 0.1538990037787702,
      "grad_norm": 0.2137439250946045,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.9969,
      "step": 112
    },
    {
      "epoch": 0.15527310202679492,
      "grad_norm": 0.15597109496593475,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.8827,
      "step": 113
    },
    {
      "epoch": 0.15664720027481965,
      "grad_norm": 0.18449462950229645,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.9033,
      "step": 114
    },
    {
      "epoch": 0.15802129852284438,
      "grad_norm": 0.1813831627368927,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.9189,
      "step": 115
    },
    {
      "epoch": 0.1593953967708691,
      "grad_norm": 0.16493883728981018,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.9033,
      "step": 116
    },
    {
      "epoch": 0.16076949501889384,
      "grad_norm": 0.16080141067504883,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8765,
      "step": 117
    },
    {
      "epoch": 0.16214359326691857,
      "grad_norm": 0.1528991460800171,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9412,
      "step": 118
    },
    {
      "epoch": 0.16351769151494333,
      "grad_norm": 0.16043640673160553,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.9105,
      "step": 119
    },
    {
      "epoch": 0.16489178976296806,
      "grad_norm": 0.1730065792798996,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8382,
      "step": 120
    },
    {
      "epoch": 0.1662658880109928,
      "grad_norm": 0.16632574796676636,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.9904,
      "step": 121
    },
    {
      "epoch": 0.16763998625901752,
      "grad_norm": 0.15896637737751007,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.8908,
      "step": 122
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 0.15873880684375763,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.9214,
      "step": 123
    },
    {
      "epoch": 0.17038818275506698,
      "grad_norm": 0.15246395766735077,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8801,
      "step": 124
    },
    {
      "epoch": 0.1717622810030917,
      "grad_norm": 0.1900641769170761,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.0458,
      "step": 125
    },
    {
      "epoch": 0.17313637925111647,
      "grad_norm": 0.18198123574256897,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.0119,
      "step": 126
    },
    {
      "epoch": 0.1745104774991412,
      "grad_norm": 0.1929614096879959,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.0394,
      "step": 127
    },
    {
      "epoch": 0.17588457574716593,
      "grad_norm": 0.20329144597053528,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.0707,
      "step": 128
    },
    {
      "epoch": 0.17725867399519066,
      "grad_norm": 0.23712950944900513,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.0767,
      "step": 129
    },
    {
      "epoch": 0.1786327722432154,
      "grad_norm": 0.22021238505840302,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.0814,
      "step": 130
    },
    {
      "epoch": 0.18000687049124012,
      "grad_norm": 0.2971738874912262,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.3107,
      "step": 131
    },
    {
      "epoch": 0.18138096873926485,
      "grad_norm": 0.26488426327705383,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.1191,
      "step": 132
    },
    {
      "epoch": 0.1827550669872896,
      "grad_norm": 0.2121073603630066,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8087,
      "step": 133
    },
    {
      "epoch": 0.18412916523531433,
      "grad_norm": 1.5958102941513062,
      "learning_rate": 2.693294185106562e-05,
      "loss": 3.1678,
      "step": 134
    },
    {
      "epoch": 0.18550326348333906,
      "grad_norm": 1.4533909559249878,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.7822,
      "step": 135
    },
    {
      "epoch": 0.1868773617313638,
      "grad_norm": 4.052315711975098,
      "learning_rate": 2.547882480847461e-05,
      "loss": 2.8424,
      "step": 136
    },
    {
      "epoch": 0.18825145997938852,
      "grad_norm": 3.7840259075164795,
      "learning_rate": 2.476172311325783e-05,
      "loss": 2.4312,
      "step": 137
    },
    {
      "epoch": 0.18962555822741325,
      "grad_norm": 0.9476276636123657,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7828,
      "step": 138
    },
    {
      "epoch": 0.19099965647543798,
      "grad_norm": 0.989886999130249,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.6125,
      "step": 139
    },
    {
      "epoch": 0.19237375472346271,
      "grad_norm": 3.8064193725585938,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.5959,
      "step": 140
    },
    {
      "epoch": 0.19374785297148747,
      "grad_norm": 3.587019443511963,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.1091,
      "step": 141
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.401906818151474,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.0817,
      "step": 142
    },
    {
      "epoch": 0.19649604946753693,
      "grad_norm": 0.2941301763057709,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8647,
      "step": 143
    },
    {
      "epoch": 0.19787014771556166,
      "grad_norm": 0.3434745669364929,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.1581,
      "step": 144
    },
    {
      "epoch": 0.1992442459635864,
      "grad_norm": 0.21999278664588928,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7988,
      "step": 145
    },
    {
      "epoch": 0.20061834421161112,
      "grad_norm": 0.2868378162384033,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.8947,
      "step": 146
    },
    {
      "epoch": 0.20199244245963585,
      "grad_norm": 0.2718929946422577,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.8061,
      "step": 147
    },
    {
      "epoch": 0.2033665407076606,
      "grad_norm": 0.33682912588119507,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.2134,
      "step": 148
    },
    {
      "epoch": 0.20474063895568534,
      "grad_norm": 0.2996339797973633,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.0755,
      "step": 149
    },
    {
      "epoch": 0.20611473720371007,
      "grad_norm": 0.37314173579216003,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.3212,
      "step": 150
    },
    {
      "epoch": 0.20611473720371007,
      "eval_loss": 1.1653245687484741,
      "eval_runtime": 34.2302,
      "eval_samples_per_second": 35.816,
      "eval_steps_per_second": 8.969,
      "step": 150
    },
    {
      "epoch": 0.2074888354517348,
      "grad_norm": 0.15887683629989624,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.8124,
      "step": 151
    },
    {
      "epoch": 0.20886293369975953,
      "grad_norm": 0.13664397597312927,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.7481,
      "step": 152
    },
    {
      "epoch": 0.21023703194778426,
      "grad_norm": 0.1605003923177719,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.9016,
      "step": 153
    },
    {
      "epoch": 0.211611130195809,
      "grad_norm": 0.1538872867822647,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.8641,
      "step": 154
    },
    {
      "epoch": 0.21298522844383375,
      "grad_norm": 0.14005528390407562,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7809,
      "step": 155
    },
    {
      "epoch": 0.21435932669185848,
      "grad_norm": 0.16359677910804749,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.8607,
      "step": 156
    },
    {
      "epoch": 0.2157334249398832,
      "grad_norm": 0.13344809412956238,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.8541,
      "step": 157
    },
    {
      "epoch": 0.21710752318790794,
      "grad_norm": 0.16984452307224274,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.9396,
      "step": 158
    },
    {
      "epoch": 0.21848162143593267,
      "grad_norm": 0.1757926493883133,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8882,
      "step": 159
    },
    {
      "epoch": 0.2198557196839574,
      "grad_norm": 0.17016346752643585,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.9038,
      "step": 160
    },
    {
      "epoch": 0.22122981793198213,
      "grad_norm": 0.15113943815231323,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.8456,
      "step": 161
    },
    {
      "epoch": 0.22260391618000688,
      "grad_norm": 0.1684754490852356,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9506,
      "step": 162
    },
    {
      "epoch": 0.2239780144280316,
      "grad_norm": 0.15492169559001923,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.9104,
      "step": 163
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 0.15392962098121643,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.8458,
      "step": 164
    },
    {
      "epoch": 0.22672621092408107,
      "grad_norm": 0.17106157541275024,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.9814,
      "step": 165
    },
    {
      "epoch": 0.2281003091721058,
      "grad_norm": 0.16319404542446136,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.9152,
      "step": 166
    },
    {
      "epoch": 0.22947440742013053,
      "grad_norm": 0.17594720423221588,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.0381,
      "step": 167
    },
    {
      "epoch": 0.23084850566815526,
      "grad_norm": 0.16697010397911072,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.9105,
      "step": 168
    },
    {
      "epoch": 0.23222260391618002,
      "grad_norm": 0.15581928193569183,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8827,
      "step": 169
    },
    {
      "epoch": 0.23359670216420475,
      "grad_norm": 0.18791039288043976,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.0107,
      "step": 170
    },
    {
      "epoch": 0.23497080041222948,
      "grad_norm": 0.17550478875637054,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.9502,
      "step": 171
    },
    {
      "epoch": 0.2363448986602542,
      "grad_norm": 0.18105049431324005,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.9119,
      "step": 172
    },
    {
      "epoch": 0.23771899690827894,
      "grad_norm": 0.16556082665920258,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.8645,
      "step": 173
    },
    {
      "epoch": 0.23909309515630367,
      "grad_norm": 0.17093637585639954,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.9089,
      "step": 174
    },
    {
      "epoch": 0.2404671934043284,
      "grad_norm": 0.18892404437065125,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.9636,
      "step": 175
    },
    {
      "epoch": 0.24184129165235313,
      "grad_norm": 0.20422516763210297,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.9971,
      "step": 176
    },
    {
      "epoch": 0.2432153899003779,
      "grad_norm": 0.1827259361743927,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.9756,
      "step": 177
    },
    {
      "epoch": 0.24458948814840262,
      "grad_norm": 0.20500867068767548,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.9437,
      "step": 178
    },
    {
      "epoch": 0.24596358639642735,
      "grad_norm": 0.24615541100502014,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.0201,
      "step": 179
    },
    {
      "epoch": 0.24733768464445208,
      "grad_norm": 0.33349740505218506,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.4211,
      "step": 180
    },
    {
      "epoch": 0.2487117828924768,
      "grad_norm": 0.2754257917404175,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.8999,
      "step": 181
    },
    {
      "epoch": 0.25008588114050156,
      "grad_norm": 1.3908370733261108,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 2.511,
      "step": 182
    },
    {
      "epoch": 0.25145997938852627,
      "grad_norm": 0.38037100434303284,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.0222,
      "step": 183
    },
    {
      "epoch": 0.252834077636551,
      "grad_norm": 3.29057240486145,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 2.0301,
      "step": 184
    },
    {
      "epoch": 0.2542081758845757,
      "grad_norm": 3.4521853923797607,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.9885,
      "step": 185
    },
    {
      "epoch": 0.2555822741326005,
      "grad_norm": 3.5108230113983154,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.7658,
      "step": 186
    },
    {
      "epoch": 0.25695637238062524,
      "grad_norm": 2.7168197631835938,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.9042,
      "step": 187
    },
    {
      "epoch": 0.25833047062864994,
      "grad_norm": 3.4009249210357666,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.7102,
      "step": 188
    },
    {
      "epoch": 0.2597045688766747,
      "grad_norm": 0.6083331108093262,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8947,
      "step": 189
    },
    {
      "epoch": 0.2610786671246994,
      "grad_norm": 3.4389724731445312,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.923,
      "step": 190
    },
    {
      "epoch": 0.26245276537272416,
      "grad_norm": 0.728319525718689,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.9702,
      "step": 191
    },
    {
      "epoch": 0.26382686362074886,
      "grad_norm": 0.24449822306632996,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.861,
      "step": 192
    },
    {
      "epoch": 0.2652009618687736,
      "grad_norm": 0.3007335066795349,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.8773,
      "step": 193
    },
    {
      "epoch": 0.2665750601167983,
      "grad_norm": 0.2735421657562256,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.8219,
      "step": 194
    },
    {
      "epoch": 0.2679491583648231,
      "grad_norm": 0.2674437463283539,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.9035,
      "step": 195
    },
    {
      "epoch": 0.26932325661284784,
      "grad_norm": 0.29353049397468567,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.0326,
      "step": 196
    },
    {
      "epoch": 0.27069735486087254,
      "grad_norm": 0.2364596575498581,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.8951,
      "step": 197
    },
    {
      "epoch": 0.2720714531088973,
      "grad_norm": 0.27734413743019104,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.878,
      "step": 198
    },
    {
      "epoch": 0.273445551356922,
      "grad_norm": 0.29012688994407654,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.1016,
      "step": 199
    },
    {
      "epoch": 0.27481964960494676,
      "grad_norm": 0.48544347286224365,
      "learning_rate": 0.0,
      "loss": 1.4588,
      "step": 200
    },
    {
      "epoch": 0.27481964960494676,
      "eval_loss": 1.1569346189498901,
      "eval_runtime": 34.2428,
      "eval_samples_per_second": 35.803,
      "eval_steps_per_second": 8.965,
      "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
}