{
  "best_metric": 0.8114035725593567,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.0067727161131382226,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.3863580565691114e-05,
      "grad_norm": 2.0550265312194824,
      "learning_rate": 1e-05,
      "loss": 1.0181,
      "step": 1
    },
    {
      "epoch": 3.3863580565691114e-05,
      "eval_loss": 1.1343133449554443,
      "eval_runtime": 4299.8291,
      "eval_samples_per_second": 11.567,
      "eval_steps_per_second": 2.892,
      "step": 1
    },
    {
      "epoch": 6.772716113138223e-05,
      "grad_norm": 3.6440083980560303,
      "learning_rate": 2e-05,
      "loss": 1.1313,
      "step": 2
    },
    {
      "epoch": 0.00010159074169707334,
      "grad_norm": 1.9653550386428833,
      "learning_rate": 3e-05,
      "loss": 1.207,
      "step": 3
    },
    {
      "epoch": 0.00013545432226276446,
      "grad_norm": 1.548991322517395,
      "learning_rate": 4e-05,
      "loss": 1.1886,
      "step": 4
    },
    {
      "epoch": 0.00016931790282845557,
      "grad_norm": 1.6184501647949219,
      "learning_rate": 5e-05,
      "loss": 1.2606,
      "step": 5
    },
    {
      "epoch": 0.00020318148339414668,
      "grad_norm": 1.5336605310440063,
      "learning_rate": 6e-05,
      "loss": 1.2318,
      "step": 6
    },
    {
      "epoch": 0.0002370450639598378,
      "grad_norm": 1.2762290239334106,
      "learning_rate": 7e-05,
      "loss": 0.9866,
      "step": 7
    },
    {
      "epoch": 0.0002709086445255289,
      "grad_norm": 1.5862436294555664,
      "learning_rate": 8e-05,
      "loss": 0.9677,
      "step": 8
    },
    {
      "epoch": 0.00030477222509122,
      "grad_norm": 1.4426425695419312,
      "learning_rate": 9e-05,
      "loss": 0.9898,
      "step": 9
    },
    {
      "epoch": 0.00033863580565691114,
      "grad_norm": 1.4509968757629395,
      "learning_rate": 0.0001,
      "loss": 1.0276,
      "step": 10
    },
    {
      "epoch": 0.0003724993862226022,
      "grad_norm": 1.492161512374878,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.0433,
      "step": 11
    },
    {
      "epoch": 0.00040636296678829337,
      "grad_norm": 1.3199902772903442,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9885,
      "step": 12
    },
    {
      "epoch": 0.00044022654735398445,
      "grad_norm": 1.301571249961853,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.941,
      "step": 13
    },
    {
      "epoch": 0.0004740901279196756,
      "grad_norm": 1.281856894493103,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.9075,
      "step": 14
    },
    {
      "epoch": 0.0005079537084853667,
      "grad_norm": 1.145501732826233,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8993,
      "step": 15
    },
    {
      "epoch": 0.0005418172890510578,
      "grad_norm": 1.1542354822158813,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8008,
      "step": 16
    },
    {
      "epoch": 0.0005756808696167489,
      "grad_norm": 1.1247410774230957,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8935,
      "step": 17
    },
    {
      "epoch": 0.00060954445018244,
      "grad_norm": 1.1652917861938477,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.81,
      "step": 18
    },
    {
      "epoch": 0.0006434080307481312,
      "grad_norm": 1.2779299020767212,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8562,
      "step": 19
    },
    {
      "epoch": 0.0006772716113138223,
      "grad_norm": 1.1494277715682983,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.9142,
      "step": 20
    },
    {
      "epoch": 0.0007111351918795134,
      "grad_norm": 1.3202309608459473,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9179,
      "step": 21
    },
    {
      "epoch": 0.0007449987724452045,
      "grad_norm": 1.0001553297042847,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8214,
      "step": 22
    },
    {
      "epoch": 0.0007788623530108956,
      "grad_norm": 1.0463453531265259,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6966,
      "step": 23
    },
    {
      "epoch": 0.0008127259335765867,
      "grad_norm": 1.2233140468597412,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8166,
      "step": 24
    },
    {
      "epoch": 0.0008465895141422778,
      "grad_norm": 1.1325368881225586,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6139,
      "step": 25
    },
    {
      "epoch": 0.0008804530947079689,
      "grad_norm": 1.083746314048767,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.6772,
      "step": 26
    },
    {
      "epoch": 0.0009143166752736601,
      "grad_norm": 1.1503418684005737,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7448,
      "step": 27
    },
    {
      "epoch": 0.0009481802558393512,
      "grad_norm": 1.0406780242919922,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6851,
      "step": 28
    },
    {
      "epoch": 0.0009820438364050424,
      "grad_norm": 1.2902339696884155,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8085,
      "step": 29
    },
    {
      "epoch": 0.0010159074169707335,
      "grad_norm": 1.2225592136383057,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7627,
      "step": 30
    },
    {
      "epoch": 0.0010497709975364246,
      "grad_norm": 1.2345811128616333,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6432,
      "step": 31
    },
    {
      "epoch": 0.0010836345781021156,
      "grad_norm": 1.408897042274475,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7066,
      "step": 32
    },
    {
      "epoch": 0.0011174981586678067,
      "grad_norm": 1.4179216623306274,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7157,
      "step": 33
    },
    {
      "epoch": 0.0011513617392334978,
      "grad_norm": 1.514042615890503,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6472,
      "step": 34
    },
    {
      "epoch": 0.001185225319799189,
      "grad_norm": 1.8889460563659668,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7806,
      "step": 35
    },
    {
      "epoch": 0.00121908890036488,
      "grad_norm": 1.725436806678772,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.7625,
      "step": 36
    },
    {
      "epoch": 0.0012529524809305713,
      "grad_norm": 1.6193572282791138,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.9422,
      "step": 37
    },
    {
      "epoch": 0.0012868160614962624,
      "grad_norm": 1.6382675170898438,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8594,
      "step": 38
    },
    {
      "epoch": 0.0013206796420619535,
      "grad_norm": 1.7415684461593628,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8809,
      "step": 39
    },
    {
      "epoch": 0.0013545432226276446,
      "grad_norm": 1.775345802307129,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7779,
      "step": 40
    },
    {
      "epoch": 0.0013884068031933356,
      "grad_norm": 2.0110960006713867,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.9585,
      "step": 41
    },
    {
      "epoch": 0.0014222703837590267,
      "grad_norm": 2.462780714035034,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8878,
      "step": 42
    },
    {
      "epoch": 0.0014561339643247178,
      "grad_norm": 2.193324565887451,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7278,
      "step": 43
    },
    {
      "epoch": 0.001489997544890409,
      "grad_norm": 2.705517053604126,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7853,
      "step": 44
    },
    {
      "epoch": 0.0015238611254561002,
      "grad_norm": 2.353170871734619,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8343,
      "step": 45
    },
    {
      "epoch": 0.0015577247060217913,
      "grad_norm": 2.479548215866089,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7577,
      "step": 46
    },
    {
      "epoch": 0.0015915882865874824,
      "grad_norm": 3.0347914695739746,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8809,
      "step": 47
    },
    {
      "epoch": 0.0016254518671531735,
      "grad_norm": 2.880753517150879,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7253,
      "step": 48
    },
    {
      "epoch": 0.0016593154477188646,
      "grad_norm": 3.1428682804107666,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.5754,
      "step": 49
    },
    {
      "epoch": 0.0016931790282845556,
      "grad_norm": 6.364545822143555,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.725,
      "step": 50
    },
    {
      "epoch": 0.0016931790282845556,
      "eval_loss": 0.9120458960533142,
      "eval_runtime": 4320.1818,
      "eval_samples_per_second": 11.512,
      "eval_steps_per_second": 2.878,
      "step": 50
    },
    {
      "epoch": 0.0017270426088502467,
      "grad_norm": 1.4226757287979126,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.1164,
      "step": 51
    },
    {
      "epoch": 0.0017609061894159378,
      "grad_norm": 1.7622880935668945,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0544,
      "step": 52
    },
    {
      "epoch": 0.0017947697699816291,
      "grad_norm": 0.964221715927124,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0363,
      "step": 53
    },
    {
      "epoch": 0.0018286333505473202,
      "grad_norm": 0.773030698299408,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.1224,
      "step": 54
    },
    {
      "epoch": 0.0018624969311130113,
      "grad_norm": 0.7979791760444641,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.1193,
      "step": 55
    },
    {
      "epoch": 0.0018963605116787024,
      "grad_norm": 0.8088381290435791,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.0557,
      "step": 56
    },
    {
      "epoch": 0.0019302240922443935,
      "grad_norm": 0.7078047394752502,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.1195,
      "step": 57
    },
    {
      "epoch": 0.0019640876728100848,
      "grad_norm": 0.8790314793586731,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.0526,
      "step": 58
    },
    {
      "epoch": 0.0019979512533757756,
      "grad_norm": 0.8600544929504395,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9374,
      "step": 59
    },
    {
      "epoch": 0.002031814833941467,
      "grad_norm": 0.9754397869110107,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8922,
      "step": 60
    },
    {
      "epoch": 0.002065678414507158,
      "grad_norm": 1.0673669576644897,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.9029,
      "step": 61
    },
    {
      "epoch": 0.002099541995072849,
      "grad_norm": 1.0809820890426636,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.803,
      "step": 62
    },
    {
      "epoch": 0.00213340557563854,
      "grad_norm": 1.1764450073242188,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.9441,
      "step": 63
    },
    {
      "epoch": 0.0021672691562042313,
      "grad_norm": 1.0016385316848755,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9902,
      "step": 64
    },
    {
      "epoch": 0.002201132736769922,
      "grad_norm": 0.8756915926933289,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7682,
      "step": 65
    },
    {
      "epoch": 0.0022349963173356135,
      "grad_norm": 0.8425341844558716,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7726,
      "step": 66
    },
    {
      "epoch": 0.0022688598979013048,
      "grad_norm": 0.9058197736740112,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8833,
      "step": 67
    },
    {
      "epoch": 0.0023027234784669956,
      "grad_norm": 0.9097495675086975,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.8457,
      "step": 68
    },
    {
      "epoch": 0.002336587059032687,
      "grad_norm": 0.9815858602523804,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8531,
      "step": 69
    },
    {
      "epoch": 0.002370450639598378,
      "grad_norm": 0.9287223815917969,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8251,
      "step": 70
    },
    {
      "epoch": 0.002404314220164069,
      "grad_norm": 0.8818957209587097,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8196,
      "step": 71
    },
    {
      "epoch": 0.00243817780072976,
      "grad_norm": 0.908197283744812,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7383,
      "step": 72
    },
    {
      "epoch": 0.0024720413812954513,
      "grad_norm": 1.0328611135482788,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7845,
      "step": 73
    },
    {
      "epoch": 0.0025059049618611426,
      "grad_norm": 0.9014108777046204,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7622,
      "step": 74
    },
    {
      "epoch": 0.0025397685424268335,
      "grad_norm": 0.9172950387001038,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8035,
      "step": 75
    },
    {
      "epoch": 0.0025736321229925248,
      "grad_norm": 0.9880456924438477,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.8214,
      "step": 76
    },
    {
      "epoch": 0.0026074957035582156,
      "grad_norm": 0.8705504536628723,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6596,
      "step": 77
    },
    {
      "epoch": 0.002641359284123907,
      "grad_norm": 0.8779760599136353,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.6849,
      "step": 78
    },
    {
      "epoch": 0.002675222864689598,
      "grad_norm": 1.0683515071868896,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7452,
      "step": 79
    },
    {
      "epoch": 0.002709086445255289,
      "grad_norm": 1.2361270189285278,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7868,
      "step": 80
    },
    {
      "epoch": 0.00274295002582098,
      "grad_norm": 1.2945915460586548,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.8237,
      "step": 81
    },
    {
      "epoch": 0.0027768136063866713,
      "grad_norm": 1.195617437362671,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7211,
      "step": 82
    },
    {
      "epoch": 0.0028106771869523626,
      "grad_norm": 1.3023602962493896,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.7865,
      "step": 83
    },
    {
      "epoch": 0.0028445407675180535,
      "grad_norm": 1.3240725994110107,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.8354,
      "step": 84
    },
    {
      "epoch": 0.0028784043480837448,
      "grad_norm": 1.4247812032699585,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.748,
      "step": 85
    },
    {
      "epoch": 0.0029122679286494356,
      "grad_norm": 1.349658489227295,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.772,
      "step": 86
    },
    {
      "epoch": 0.002946131509215127,
      "grad_norm": 1.5455256700515747,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7621,
      "step": 87
    },
    {
      "epoch": 0.002979995089780818,
      "grad_norm": 1.7216026782989502,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7189,
      "step": 88
    },
    {
      "epoch": 0.003013858670346509,
      "grad_norm": 1.6525294780731201,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8356,
      "step": 89
    },
    {
      "epoch": 0.0030477222509122004,
      "grad_norm": 1.6729861497879028,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7422,
      "step": 90
    },
    {
      "epoch": 0.0030815858314778913,
      "grad_norm": 1.6616734266281128,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6948,
      "step": 91
    },
    {
      "epoch": 0.0031154494120435826,
      "grad_norm": 1.6144821643829346,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7476,
      "step": 92
    },
    {
      "epoch": 0.0031493129926092735,
      "grad_norm": 1.685961127281189,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7543,
      "step": 93
    },
    {
      "epoch": 0.0031831765731749648,
      "grad_norm": 2.659148693084717,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.764,
      "step": 94
    },
    {
      "epoch": 0.0032170401537406556,
      "grad_norm": 21.882776260375977,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7739,
      "step": 95
    },
    {
      "epoch": 0.003250903734306347,
      "grad_norm": 2.230511426925659,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7715,
      "step": 96
    },
    {
      "epoch": 0.003284767314872038,
      "grad_norm": 2.5464425086975098,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7734,
      "step": 97
    },
    {
      "epoch": 0.003318630895437729,
      "grad_norm": 2.8798375129699707,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.8209,
      "step": 98
    },
    {
      "epoch": 0.0033524944760034204,
      "grad_norm": 4.405345439910889,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7309,
      "step": 99
    },
    {
      "epoch": 0.0033863580565691113,
      "grad_norm": 4.10702657699585,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8177,
      "step": 100
    },
    {
      "epoch": 0.0033863580565691113,
      "eval_loss": 0.852568507194519,
      "eval_runtime": 4317.292,
      "eval_samples_per_second": 11.52,
      "eval_steps_per_second": 2.88,
      "step": 100
    },
    {
      "epoch": 0.0034202216371348026,
      "grad_norm": 1.1645525693893433,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.8586,
      "step": 101
    },
    {
      "epoch": 0.0034540852177004935,
      "grad_norm": 1.1815965175628662,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.3288,
      "step": 102
    },
    {
      "epoch": 0.0034879487982661848,
      "grad_norm": 0.9404454231262207,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9437,
      "step": 103
    },
    {
      "epoch": 0.0035218123788318756,
      "grad_norm": 0.802773118019104,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.027,
      "step": 104
    },
    {
      "epoch": 0.003555675959397567,
      "grad_norm": 0.761770486831665,
      "learning_rate": 5e-05,
      "loss": 1.0444,
      "step": 105
    },
    {
      "epoch": 0.0035895395399632582,
      "grad_norm": 0.8026449084281921,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.0423,
      "step": 106
    },
    {
      "epoch": 0.003623403120528949,
      "grad_norm": 0.7439582347869873,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.0818,
      "step": 107
    },
    {
      "epoch": 0.0036572667010946404,
      "grad_norm": 0.9292482137680054,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.9144,
      "step": 108
    },
    {
      "epoch": 0.0036911302816603313,
      "grad_norm": 0.8468343615531921,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.9942,
      "step": 109
    },
    {
      "epoch": 0.0037249938622260226,
      "grad_norm": 0.9255709052085876,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8896,
      "step": 110
    },
    {
      "epoch": 0.0037588574427917134,
      "grad_norm": 1.1478493213653564,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9313,
      "step": 111
    },
    {
      "epoch": 0.0037927210233574048,
      "grad_norm": 0.9958303570747375,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.894,
      "step": 112
    },
    {
      "epoch": 0.0038265846039230956,
      "grad_norm": 0.8531522750854492,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.1062,
      "step": 113
    },
    {
      "epoch": 0.003860448184488787,
      "grad_norm": 0.8338115215301514,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.9819,
      "step": 114
    },
    {
      "epoch": 0.0038943117650544782,
      "grad_norm": 0.8781588077545166,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8914,
      "step": 115
    },
    {
      "epoch": 0.0039281753456201695,
      "grad_norm": 0.8628450632095337,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.859,
      "step": 116
    },
    {
      "epoch": 0.00396203892618586,
      "grad_norm": 0.9441609382629395,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9065,
      "step": 117
    },
    {
      "epoch": 0.003995902506751551,
      "grad_norm": 0.8835806846618652,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7714,
      "step": 118
    },
    {
      "epoch": 0.004029766087317243,
      "grad_norm": 0.8470550179481506,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7913,
      "step": 119
    },
    {
      "epoch": 0.004063629667882934,
      "grad_norm": 0.823840320110321,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7686,
      "step": 120
    },
    {
      "epoch": 0.004097493248448624,
      "grad_norm": 0.9964772462844849,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7821,
      "step": 121
    },
    {
      "epoch": 0.004131356829014316,
      "grad_norm": 0.8445329666137695,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7733,
      "step": 122
    },
    {
      "epoch": 0.004165220409580007,
      "grad_norm": 0.8473560214042664,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.8337,
      "step": 123
    },
    {
      "epoch": 0.004199083990145698,
      "grad_norm": 0.8527365922927856,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7192,
      "step": 124
    },
    {
      "epoch": 0.0042329475707113895,
      "grad_norm": 0.8579614162445068,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7804,
      "step": 125
    },
    {
      "epoch": 0.00426681115127708,
      "grad_norm": 0.9332769513130188,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7645,
      "step": 126
    },
    {
      "epoch": 0.004300674731842771,
      "grad_norm": 0.9274150729179382,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7164,
      "step": 127
    },
    {
      "epoch": 0.004334538312408463,
      "grad_norm": 0.9002189040184021,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7174,
      "step": 128
    },
    {
      "epoch": 0.004368401892974154,
      "grad_norm": 1.0153923034667969,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7442,
      "step": 129
    },
    {
      "epoch": 0.004402265473539844,
      "grad_norm": 1.0742350816726685,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7463,
      "step": 130
    },
    {
      "epoch": 0.004436129054105536,
      "grad_norm": 1.1177161931991577,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7075,
      "step": 131
    },
    {
      "epoch": 0.004469992634671227,
      "grad_norm": 1.162717580795288,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7061,
      "step": 132
    },
    {
      "epoch": 0.004503856215236918,
      "grad_norm": 1.1704574823379517,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7916,
      "step": 133
    },
    {
      "epoch": 0.0045377197958026095,
      "grad_norm": 1.3212155103683472,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.77,
      "step": 134
    },
    {
      "epoch": 0.0045715833763683,
      "grad_norm": 1.30833101272583,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7571,
      "step": 135
    },
    {
      "epoch": 0.004605446956933991,
      "grad_norm": 1.5746608972549438,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.8028,
      "step": 136
    },
    {
      "epoch": 0.004639310537499683,
      "grad_norm": 1.3676880598068237,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7521,
      "step": 137
    },
    {
      "epoch": 0.004673174118065374,
      "grad_norm": 1.3884906768798828,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8115,
      "step": 138
    },
    {
      "epoch": 0.004707037698631065,
      "grad_norm": 1.6474037170410156,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7672,
      "step": 139
    },
    {
      "epoch": 0.004740901279196756,
      "grad_norm": 1.9243255853652954,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7169,
      "step": 140
    },
    {
      "epoch": 0.004774764859762447,
      "grad_norm": 1.6813877820968628,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7787,
      "step": 141
    },
    {
      "epoch": 0.004808628440328138,
      "grad_norm": 1.7100144624710083,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.796,
      "step": 142
    },
    {
      "epoch": 0.0048424920208938295,
      "grad_norm": 1.7141149044036865,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7068,
      "step": 143
    },
    {
      "epoch": 0.00487635560145952,
      "grad_norm": 1.9750072956085205,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.8144,
      "step": 144
    },
    {
      "epoch": 0.004910219182025211,
      "grad_norm": 2.454282760620117,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7961,
      "step": 145
    },
    {
      "epoch": 0.004944082762590903,
      "grad_norm": 2.3081367015838623,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.8827,
      "step": 146
    },
    {
      "epoch": 0.004977946343156594,
      "grad_norm": 2.574387311935425,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6805,
      "step": 147
    },
    {
      "epoch": 0.005011809923722285,
      "grad_norm": 2.641726016998291,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.6993,
      "step": 148
    },
    {
      "epoch": 0.005045673504287976,
      "grad_norm": 3.345205068588257,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.4848,
      "step": 149
    },
    {
      "epoch": 0.005079537084853667,
      "grad_norm": 3.6035573482513428,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5473,
      "step": 150
    },
    {
      "epoch": 0.005079537084853667,
      "eval_loss": 0.8155261874198914,
      "eval_runtime": 4317.678,
      "eval_samples_per_second": 11.519,
      "eval_steps_per_second": 2.88,
      "step": 150
    },
    {
      "epoch": 0.005113400665419358,
      "grad_norm": 1.0169190168380737,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.075,
      "step": 151
    },
    {
      "epoch": 0.0051472642459850495,
      "grad_norm": 1.1990779638290405,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.1115,
      "step": 152
    },
    {
      "epoch": 0.00518112782655074,
      "grad_norm": 1.2795466184616089,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.1917,
      "step": 153
    },
    {
      "epoch": 0.005214991407116431,
      "grad_norm": 0.8081529140472412,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.0735,
      "step": 154
    },
    {
      "epoch": 0.005248854987682123,
      "grad_norm": 0.6913602948188782,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.0835,
      "step": 155
    },
    {
      "epoch": 0.005282718568247814,
      "grad_norm": 0.6684243679046631,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.0837,
      "step": 156
    },
    {
      "epoch": 0.005316582148813505,
      "grad_norm": 0.7527070045471191,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.1056,
      "step": 157
    },
    {
      "epoch": 0.005350445729379196,
      "grad_norm": 0.865993082523346,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.9421,
      "step": 158
    },
    {
      "epoch": 0.005384309309944887,
      "grad_norm": 0.7906056046485901,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.9133,
      "step": 159
    },
    {
      "epoch": 0.005418172890510578,
      "grad_norm": 0.9160190224647522,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.768,
      "step": 160
    },
    {
      "epoch": 0.0054520364710762695,
      "grad_norm": 1.043424129486084,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.818,
      "step": 161
    },
    {
      "epoch": 0.00548590005164196,
      "grad_norm": 0.8910501599311829,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9083,
      "step": 162
    },
    {
      "epoch": 0.005519763632207651,
      "grad_norm": 1.228179931640625,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.0135,
      "step": 163
    },
    {
      "epoch": 0.0055536272127733426,
      "grad_norm": 0.9631962180137634,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.9442,
      "step": 164
    },
    {
      "epoch": 0.005587490793339034,
      "grad_norm": 0.913136899471283,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.894,
      "step": 165
    },
    {
      "epoch": 0.005621354373904725,
      "grad_norm": 0.8917601108551025,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.8381,
      "step": 166
    },
    {
      "epoch": 0.005655217954470416,
      "grad_norm": 0.8912904262542725,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7346,
      "step": 167
    },
    {
      "epoch": 0.005689081535036107,
      "grad_norm": 0.7889885902404785,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8449,
      "step": 168
    },
    {
      "epoch": 0.005722945115601798,
      "grad_norm": 0.8853978514671326,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8217,
      "step": 169
    },
    {
      "epoch": 0.0057568086961674895,
      "grad_norm": 0.9979472160339355,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.9012,
      "step": 170
    },
    {
      "epoch": 0.00579067227673318,
      "grad_norm": 0.9669233560562134,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7958,
      "step": 171
    },
    {
      "epoch": 0.005824535857298871,
      "grad_norm": 0.8295865654945374,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.8278,
      "step": 172
    },
    {
      "epoch": 0.0058583994378645626,
      "grad_norm": 0.9383924603462219,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.83,
      "step": 173
    },
    {
      "epoch": 0.005892263018430254,
      "grad_norm": 1.0331565141677856,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.6505,
      "step": 174
    },
    {
      "epoch": 0.005926126598995945,
      "grad_norm": 0.8853581547737122,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.8621,
      "step": 175
    },
    {
      "epoch": 0.005959990179561636,
      "grad_norm": 0.8971402049064636,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.7499,
      "step": 176
    },
    {
      "epoch": 0.005993853760127327,
      "grad_norm": 0.9665986895561218,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7148,
      "step": 177
    },
    {
      "epoch": 0.006027717340693018,
      "grad_norm": 0.9865388870239258,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7347,
      "step": 178
    },
    {
      "epoch": 0.0060615809212587095,
      "grad_norm": 1.0266306400299072,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.728,
      "step": 179
    },
    {
      "epoch": 0.006095444501824401,
      "grad_norm": 0.9568273425102234,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6781,
      "step": 180
    },
    {
      "epoch": 0.006129308082390091,
      "grad_norm": 1.2367172241210938,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6484,
      "step": 181
    },
    {
      "epoch": 0.0061631716629557826,
      "grad_norm": 1.1872228384017944,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.7359,
      "step": 182
    },
    {
      "epoch": 0.006197035243521474,
      "grad_norm": 1.4293206930160522,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.8395,
      "step": 183
    },
    {
      "epoch": 0.006230898824087165,
      "grad_norm": 1.1669307947158813,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.754,
      "step": 184
    },
    {
      "epoch": 0.006264762404652856,
      "grad_norm": 1.3672001361846924,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7963,
      "step": 185
    },
    {
      "epoch": 0.006298625985218547,
      "grad_norm": 1.3376007080078125,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.663,
      "step": 186
    },
    {
      "epoch": 0.006332489565784238,
      "grad_norm": 1.366632103919983,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8245,
      "step": 187
    },
    {
      "epoch": 0.0063663531463499295,
      "grad_norm": 1.5080217123031616,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.7522,
      "step": 188
    },
    {
      "epoch": 0.006400216726915621,
      "grad_norm": 1.6256979703903198,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.832,
      "step": 189
    },
    {
      "epoch": 0.006434080307481311,
      "grad_norm": 1.8914995193481445,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.7757,
      "step": 190
    },
    {
      "epoch": 0.0064679438880470026,
      "grad_norm": 1.4612499475479126,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.654,
      "step": 191
    },
    {
      "epoch": 0.006501807468612694,
      "grad_norm": 1.890237808227539,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7451,
      "step": 192
    },
    {
      "epoch": 0.006535671049178385,
      "grad_norm": 2.175194025039673,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7637,
      "step": 193
    },
    {
      "epoch": 0.006569534629744076,
      "grad_norm": 2.0705788135528564,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.9006,
      "step": 194
    },
    {
      "epoch": 0.006603398210309767,
      "grad_norm": 1.832811951637268,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.669,
      "step": 195
    },
    {
      "epoch": 0.006637261790875458,
      "grad_norm": 3.1343774795532227,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.7918,
      "step": 196
    },
    {
      "epoch": 0.0066711253714411495,
      "grad_norm": 2.2302896976470947,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.7936,
      "step": 197
    },
    {
      "epoch": 0.006704988952006841,
      "grad_norm": 2.6118152141571045,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.7689,
      "step": 198
    },
    {
      "epoch": 0.006738852532572531,
      "grad_norm": 3.110301971435547,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6301,
      "step": 199
    },
    {
      "epoch": 0.0067727161131382226,
      "grad_norm": 3.1405715942382812,
      "learning_rate": 0.0,
      "loss": 0.5723,
      "step": 200
    },
    {
      "epoch": 0.0067727161131382226,
      "eval_loss": 0.8114035725593567,
      "eval_runtime": 4311.9054,
      "eval_samples_per_second": 11.534,
      "eval_steps_per_second": 2.884,
      "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": 3.0737300270874624e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}