{
  "best_metric": 0.3519905209541321,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.0540184453227932,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005270092226613966,
      "grad_norm": 0.36007922887802124,
      "learning_rate": 1e-05,
      "loss": 0.971,
      "step": 1
    },
    {
      "epoch": 0.005270092226613966,
      "eval_loss": 2.119786024093628,
      "eval_runtime": 43.7512,
      "eval_samples_per_second": 7.314,
      "eval_steps_per_second": 1.829,
      "step": 1
    },
    {
      "epoch": 0.010540184453227932,
      "grad_norm": 0.37956202030181885,
      "learning_rate": 2e-05,
      "loss": 0.9456,
      "step": 2
    },
    {
      "epoch": 0.015810276679841896,
      "grad_norm": 0.3960096836090088,
      "learning_rate": 3e-05,
      "loss": 0.9817,
      "step": 3
    },
    {
      "epoch": 0.021080368906455864,
      "grad_norm": 0.4393172264099121,
      "learning_rate": 4e-05,
      "loss": 0.987,
      "step": 4
    },
    {
      "epoch": 0.026350461133069828,
      "grad_norm": 0.45205584168434143,
      "learning_rate": 5e-05,
      "loss": 0.9841,
      "step": 5
    },
    {
      "epoch": 0.03162055335968379,
      "grad_norm": 0.42530569434165955,
      "learning_rate": 6e-05,
      "loss": 0.9245,
      "step": 6
    },
    {
      "epoch": 0.03689064558629776,
      "grad_norm": 0.3607157766819,
      "learning_rate": 7e-05,
      "loss": 0.8981,
      "step": 7
    },
    {
      "epoch": 0.04216073781291173,
      "grad_norm": 0.3384549915790558,
      "learning_rate": 8e-05,
      "loss": 0.8303,
      "step": 8
    },
    {
      "epoch": 0.04743083003952569,
      "grad_norm": 0.294120192527771,
      "learning_rate": 9e-05,
      "loss": 0.7917,
      "step": 9
    },
    {
      "epoch": 0.052700922266139656,
      "grad_norm": 0.31573590636253357,
      "learning_rate": 0.0001,
      "loss": 0.7055,
      "step": 10
    },
    {
      "epoch": 0.057971014492753624,
      "grad_norm": 0.32332369685173035,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7288,
      "step": 11
    },
    {
      "epoch": 0.06324110671936758,
      "grad_norm": 0.33200111985206604,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6646,
      "step": 12
    },
    {
      "epoch": 0.06851119894598155,
      "grad_norm": 0.3049176037311554,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6715,
      "step": 13
    },
    {
      "epoch": 0.07378129117259552,
      "grad_norm": 0.2885645627975464,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7104,
      "step": 14
    },
    {
      "epoch": 0.07905138339920949,
      "grad_norm": 0.29562580585479736,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7032,
      "step": 15
    },
    {
      "epoch": 0.08432147562582346,
      "grad_norm": 0.250317245721817,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.6483,
      "step": 16
    },
    {
      "epoch": 0.08959156785243742,
      "grad_norm": 0.23009562492370605,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6435,
      "step": 17
    },
    {
      "epoch": 0.09486166007905138,
      "grad_norm": 0.2375568300485611,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.557,
      "step": 18
    },
    {
      "epoch": 0.10013175230566534,
      "grad_norm": 0.25071313977241516,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6184,
      "step": 19
    },
    {
      "epoch": 0.10540184453227931,
      "grad_norm": 0.25776422023773193,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6078,
      "step": 20
    },
    {
      "epoch": 0.11067193675889328,
      "grad_norm": 0.22023747861385345,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.5358,
      "step": 21
    },
    {
      "epoch": 0.11594202898550725,
      "grad_norm": 0.20834621787071228,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.4954,
      "step": 22
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.25106146931648254,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.5658,
      "step": 23
    },
    {
      "epoch": 0.12648221343873517,
      "grad_norm": 0.2441634237766266,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.502,
      "step": 24
    },
    {
      "epoch": 0.13175230566534915,
      "grad_norm": 0.22364813089370728,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4787,
      "step": 25
    },
    {
      "epoch": 0.1370223978919631,
      "grad_norm": 0.2380867451429367,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.5488,
      "step": 26
    },
    {
      "epoch": 0.1422924901185771,
      "grad_norm": 0.23539209365844727,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.5746,
      "step": 27
    },
    {
      "epoch": 0.14756258234519104,
      "grad_norm": 0.2205914556980133,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4917,
      "step": 28
    },
    {
      "epoch": 0.152832674571805,
      "grad_norm": 0.22702962160110474,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4237,
      "step": 29
    },
    {
      "epoch": 0.15810276679841898,
      "grad_norm": 0.1952887922525406,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4501,
      "step": 30
    },
    {
      "epoch": 0.16337285902503293,
      "grad_norm": 0.21436293423175812,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4626,
      "step": 31
    },
    {
      "epoch": 0.1686429512516469,
      "grad_norm": 0.24102115631103516,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.4011,
      "step": 32
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.2348122000694275,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.3774,
      "step": 33
    },
    {
      "epoch": 0.17918313570487485,
      "grad_norm": 0.2113296240568161,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3718,
      "step": 34
    },
    {
      "epoch": 0.1844532279314888,
      "grad_norm": 0.2504887580871582,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3906,
      "step": 35
    },
    {
      "epoch": 0.18972332015810275,
      "grad_norm": 0.28196996450424194,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3491,
      "step": 36
    },
    {
      "epoch": 0.19499341238471674,
      "grad_norm": 4.921154975891113,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.6316,
      "step": 37
    },
    {
      "epoch": 0.2002635046113307,
      "grad_norm": 23.163225173950195,
      "learning_rate": 9.473646649103818e-05,
      "loss": 8.8471,
      "step": 38
    },
    {
      "epoch": 0.20553359683794467,
      "grad_norm": 11.425708770751953,
      "learning_rate": 9.43611409721806e-05,
      "loss": 5.8589,
      "step": 39
    },
    {
      "epoch": 0.21080368906455862,
      "grad_norm": 8.346053123474121,
      "learning_rate": 9.397368756032445e-05,
      "loss": 4.3121,
      "step": 40
    },
    {
      "epoch": 0.2160737812911726,
      "grad_norm": 6.085128307342529,
      "learning_rate": 9.357421218136386e-05,
      "loss": 3.1223,
      "step": 41
    },
    {
      "epoch": 0.22134387351778656,
      "grad_norm": 3.9048242568969727,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.2365,
      "step": 42
    },
    {
      "epoch": 0.22661396574440051,
      "grad_norm": 4.700796127319336,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.6328,
      "step": 43
    },
    {
      "epoch": 0.2318840579710145,
      "grad_norm": 9.7023344039917,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.0165,
      "step": 44
    },
    {
      "epoch": 0.23715415019762845,
      "grad_norm": 3.366584539413452,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5992,
      "step": 45
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 1.7050577402114868,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.2181,
      "step": 46
    },
    {
      "epoch": 0.24769433465085638,
      "grad_norm": 4.42706298828125,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.1202,
      "step": 47
    },
    {
      "epoch": 0.25296442687747034,
      "grad_norm": 63.237709045410156,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.2668,
      "step": 48
    },
    {
      "epoch": 0.25823451910408435,
      "grad_norm": 9.860939025878906,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1686,
      "step": 49
    },
    {
      "epoch": 0.2635046113306983,
      "grad_norm": 1.8445277214050293,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.8614,
      "step": 50
    },
    {
      "epoch": 0.2635046113306983,
      "eval_loss": 0.6654142141342163,
      "eval_runtime": 44.7877,
      "eval_samples_per_second": 7.145,
      "eval_steps_per_second": 1.786,
      "step": 50
    },
    {
      "epoch": 0.26877470355731226,
      "grad_norm": 0.8604763746261597,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.748,
      "step": 51
    },
    {
      "epoch": 0.2740447957839262,
      "grad_norm": 0.48581191897392273,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.64,
      "step": 52
    },
    {
      "epoch": 0.27931488801054016,
      "grad_norm": 0.3265190124511719,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6123,
      "step": 53
    },
    {
      "epoch": 0.2845849802371542,
      "grad_norm": 0.2904956340789795,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.627,
      "step": 54
    },
    {
      "epoch": 0.2898550724637681,
      "grad_norm": 0.2529054582118988,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6016,
      "step": 55
    },
    {
      "epoch": 0.2951251646903821,
      "grad_norm": 0.25748005509376526,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.5669,
      "step": 56
    },
    {
      "epoch": 0.30039525691699603,
      "grad_norm": 0.2544119954109192,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.5643,
      "step": 57
    },
    {
      "epoch": 0.30566534914361,
      "grad_norm": 0.2299002856016159,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5743,
      "step": 58
    },
    {
      "epoch": 0.310935441370224,
      "grad_norm": 0.23421917855739594,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.5667,
      "step": 59
    },
    {
      "epoch": 0.31620553359683795,
      "grad_norm": 0.2180004119873047,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.5364,
      "step": 60
    },
    {
      "epoch": 0.3214756258234519,
      "grad_norm": 0.22186800837516785,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6297,
      "step": 61
    },
    {
      "epoch": 0.32674571805006586,
      "grad_norm": 0.2175266295671463,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5418,
      "step": 62
    },
    {
      "epoch": 0.33201581027667987,
      "grad_norm": 0.20032264292240143,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5367,
      "step": 63
    },
    {
      "epoch": 0.3372859025032938,
      "grad_norm": 0.2110578566789627,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.5335,
      "step": 64
    },
    {
      "epoch": 0.3425559947299078,
      "grad_norm": 0.19011196494102478,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5246,
      "step": 65
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.20325867831707,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.4866,
      "step": 66
    },
    {
      "epoch": 0.3530961791831357,
      "grad_norm": 0.1881006807088852,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5035,
      "step": 67
    },
    {
      "epoch": 0.3583662714097497,
      "grad_norm": 0.1962674856185913,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.4688,
      "step": 68
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.18628805875778198,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4911,
      "step": 69
    },
    {
      "epoch": 0.3689064558629776,
      "grad_norm": 0.20440946519374847,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.4968,
      "step": 70
    },
    {
      "epoch": 0.37417654808959155,
      "grad_norm": 0.19114923477172852,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.4753,
      "step": 71
    },
    {
      "epoch": 0.3794466403162055,
      "grad_norm": 0.18696175515651703,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4187,
      "step": 72
    },
    {
      "epoch": 0.3847167325428195,
      "grad_norm": 0.1871793568134308,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.4484,
      "step": 73
    },
    {
      "epoch": 0.38998682476943347,
      "grad_norm": 0.19794553518295288,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.4244,
      "step": 74
    },
    {
      "epoch": 0.3952569169960474,
      "grad_norm": 0.20902219414710999,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.45,
      "step": 75
    },
    {
      "epoch": 0.4005270092226614,
      "grad_norm": 0.18148957192897797,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.3762,
      "step": 76
    },
    {
      "epoch": 0.4057971014492754,
      "grad_norm": 0.19109255075454712,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.4094,
      "step": 77
    },
    {
      "epoch": 0.41106719367588934,
      "grad_norm": 0.22653619945049286,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.3765,
      "step": 78
    },
    {
      "epoch": 0.4163372859025033,
      "grad_norm": 0.19191308319568634,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.3569,
      "step": 79
    },
    {
      "epoch": 0.42160737812911725,
      "grad_norm": 0.19180797040462494,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4658,
      "step": 80
    },
    {
      "epoch": 0.4268774703557312,
      "grad_norm": 0.20571114122867584,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.372,
      "step": 81
    },
    {
      "epoch": 0.4321475625823452,
      "grad_norm": 0.1984131932258606,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3347,
      "step": 82
    },
    {
      "epoch": 0.43741765480895917,
      "grad_norm": 0.23018479347229004,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.349,
      "step": 83
    },
    {
      "epoch": 0.4426877470355731,
      "grad_norm": 0.22268223762512207,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3679,
      "step": 84
    },
    {
      "epoch": 0.4479578392621871,
      "grad_norm": 0.2689175009727478,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.2892,
      "step": 85
    },
    {
      "epoch": 0.45322793148880103,
      "grad_norm": 7.742241859436035,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5144,
      "step": 86
    },
    {
      "epoch": 0.45849802371541504,
      "grad_norm": 4.821127414703369,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.0287,
      "step": 87
    },
    {
      "epoch": 0.463768115942029,
      "grad_norm": 3.3412952423095703,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.5334,
      "step": 88
    },
    {
      "epoch": 0.46903820816864294,
      "grad_norm": 2.0001614093780518,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.2903,
      "step": 89
    },
    {
      "epoch": 0.4743083003952569,
      "grad_norm": 1.5088772773742676,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1814,
      "step": 90
    },
    {
      "epoch": 0.4795783926218709,
      "grad_norm": 1.2217334508895874,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.1207,
      "step": 91
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.4933153986930847,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0395,
      "step": 92
    },
    {
      "epoch": 0.4901185770750988,
      "grad_norm": 0.13398855924606323,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0105,
      "step": 93
    },
    {
      "epoch": 0.49538866930171277,
      "grad_norm": 0.10246367752552032,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0041,
      "step": 94
    },
    {
      "epoch": 0.5006587615283268,
      "grad_norm": 0.43560096621513367,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6922,
      "step": 95
    },
    {
      "epoch": 0.5059288537549407,
      "grad_norm": 0.38687416911125183,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.6581,
      "step": 96
    },
    {
      "epoch": 0.5111989459815547,
      "grad_norm": 0.2983827292919159,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.5803,
      "step": 97
    },
    {
      "epoch": 0.5164690382081687,
      "grad_norm": 0.2499283105134964,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5447,
      "step": 98
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.2374754250049591,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.599,
      "step": 99
    },
    {
      "epoch": 0.5270092226613966,
      "grad_norm": 0.19526469707489014,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5229,
      "step": 100
    },
    {
      "epoch": 0.5270092226613966,
      "eval_loss": 0.402304083108902,
      "eval_runtime": 44.8081,
      "eval_samples_per_second": 7.142,
      "eval_steps_per_second": 1.785,
      "step": 100
    },
    {
      "epoch": 0.5322793148880105,
      "grad_norm": 0.19402065873146057,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.5324,
      "step": 101
    },
    {
      "epoch": 0.5375494071146245,
      "grad_norm": 0.20999035239219666,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5723,
      "step": 102
    },
    {
      "epoch": 0.5428194993412385,
      "grad_norm": 0.2194211632013321,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5599,
      "step": 103
    },
    {
      "epoch": 0.5480895915678524,
      "grad_norm": 0.21826831996440887,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5125,
      "step": 104
    },
    {
      "epoch": 0.5533596837944664,
      "grad_norm": 0.20076434314250946,
      "learning_rate": 5e-05,
      "loss": 0.5272,
      "step": 105
    },
    {
      "epoch": 0.5586297760210803,
      "grad_norm": 0.1974741369485855,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.5769,
      "step": 106
    },
    {
      "epoch": 0.5638998682476943,
      "grad_norm": 0.1888551563024521,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.5628,
      "step": 107
    },
    {
      "epoch": 0.5691699604743083,
      "grad_norm": 0.19507338106632233,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.4896,
      "step": 108
    },
    {
      "epoch": 0.5744400527009222,
      "grad_norm": 0.22944696247577667,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.5502,
      "step": 109
    },
    {
      "epoch": 0.5797101449275363,
      "grad_norm": 0.21223241090774536,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.5328,
      "step": 110
    },
    {
      "epoch": 0.5849802371541502,
      "grad_norm": 0.20847904682159424,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5282,
      "step": 111
    },
    {
      "epoch": 0.5902503293807642,
      "grad_norm": 0.20309780538082123,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.4764,
      "step": 112
    },
    {
      "epoch": 0.5955204216073782,
      "grad_norm": 0.1928689032793045,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.4732,
      "step": 113
    },
    {
      "epoch": 0.6007905138339921,
      "grad_norm": 0.204689159989357,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.535,
      "step": 114
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.21241801977157593,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.5135,
      "step": 115
    },
    {
      "epoch": 0.61133069828722,
      "grad_norm": 0.2158992886543274,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5116,
      "step": 116
    },
    {
      "epoch": 0.616600790513834,
      "grad_norm": 0.21113267540931702,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4757,
      "step": 117
    },
    {
      "epoch": 0.621870882740448,
      "grad_norm": 0.21639497578144073,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.5233,
      "step": 118
    },
    {
      "epoch": 0.6271409749670619,
      "grad_norm": 0.22403116524219513,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.4511,
      "step": 119
    },
    {
      "epoch": 0.6324110671936759,
      "grad_norm": 0.21138609945774078,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.4143,
      "step": 120
    },
    {
      "epoch": 0.6376811594202898,
      "grad_norm": 0.20197531580924988,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.4413,
      "step": 121
    },
    {
      "epoch": 0.6429512516469038,
      "grad_norm": 0.20211012661457062,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.4471,
      "step": 122
    },
    {
      "epoch": 0.6482213438735178,
      "grad_norm": 0.1884700357913971,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.4511,
      "step": 123
    },
    {
      "epoch": 0.6534914361001317,
      "grad_norm": 0.19700978696346283,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.4414,
      "step": 124
    },
    {
      "epoch": 0.6587615283267457,
      "grad_norm": 0.18611428141593933,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4201,
      "step": 125
    },
    {
      "epoch": 0.6640316205533597,
      "grad_norm": 0.1683787703514099,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3313,
      "step": 126
    },
    {
      "epoch": 0.6693017127799736,
      "grad_norm": 0.19195891916751862,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.3788,
      "step": 127
    },
    {
      "epoch": 0.6745718050065876,
      "grad_norm": 0.18323451280593872,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.3722,
      "step": 128
    },
    {
      "epoch": 0.6798418972332015,
      "grad_norm": 0.19621214270591736,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3343,
      "step": 129
    },
    {
      "epoch": 0.6851119894598156,
      "grad_norm": 0.19653381407260895,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.2715,
      "step": 130
    },
    {
      "epoch": 0.6903820816864296,
      "grad_norm": 0.2606562376022339,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.2853,
      "step": 131
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 7.113873481750488,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.9114,
      "step": 132
    },
    {
      "epoch": 0.7009222661396575,
      "grad_norm": 6.882251262664795,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8387,
      "step": 133
    },
    {
      "epoch": 0.7061923583662714,
      "grad_norm": 6.385800361633301,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6618,
      "step": 134
    },
    {
      "epoch": 0.7114624505928854,
      "grad_norm": 4.503515243530273,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.3245,
      "step": 135
    },
    {
      "epoch": 0.7167325428194994,
      "grad_norm": 2.887765884399414,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1654,
      "step": 136
    },
    {
      "epoch": 0.7220026350461133,
      "grad_norm": 1.1690983772277832,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0578,
      "step": 137
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.351256400346756,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0188,
      "step": 138
    },
    {
      "epoch": 0.7325428194993412,
      "grad_norm": 0.1889435350894928,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.011,
      "step": 139
    },
    {
      "epoch": 0.7378129117259552,
      "grad_norm": 0.08565651625394821,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0048,
      "step": 140
    },
    {
      "epoch": 0.7430830039525692,
      "grad_norm": 0.014903017319738865,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0006,
      "step": 141
    },
    {
      "epoch": 0.7483530961791831,
      "grad_norm": 0.23479479551315308,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6041,
      "step": 142
    },
    {
      "epoch": 0.7536231884057971,
      "grad_norm": 0.21435822546482086,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5156,
      "step": 143
    },
    {
      "epoch": 0.758893280632411,
      "grad_norm": 0.21738499402999878,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5187,
      "step": 144
    },
    {
      "epoch": 0.764163372859025,
      "grad_norm": 0.19473646581172943,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.5494,
      "step": 145
    },
    {
      "epoch": 0.769433465085639,
      "grad_norm": 0.2030380517244339,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5073,
      "step": 146
    },
    {
      "epoch": 0.7747035573122529,
      "grad_norm": 0.17968852818012238,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.4955,
      "step": 147
    },
    {
      "epoch": 0.7799736495388669,
      "grad_norm": 0.19527874886989594,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5262,
      "step": 148
    },
    {
      "epoch": 0.7852437417654808,
      "grad_norm": 0.17301662266254425,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5533,
      "step": 149
    },
    {
      "epoch": 0.7905138339920948,
      "grad_norm": 0.16860952973365784,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.4709,
      "step": 150
    },
    {
      "epoch": 0.7905138339920948,
      "eval_loss": 0.3691801130771637,
      "eval_runtime": 44.8707,
      "eval_samples_per_second": 7.132,
      "eval_steps_per_second": 1.783,
      "step": 150
    },
    {
      "epoch": 0.7957839262187089,
      "grad_norm": 0.17219588160514832,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5471,
      "step": 151
    },
    {
      "epoch": 0.8010540184453228,
      "grad_norm": 0.18737190961837769,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4981,
      "step": 152
    },
    {
      "epoch": 0.8063241106719368,
      "grad_norm": 0.1885117143392563,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.514,
      "step": 153
    },
    {
      "epoch": 0.8115942028985508,
      "grad_norm": 0.19386544823646545,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.4789,
      "step": 154
    },
    {
      "epoch": 0.8168642951251647,
      "grad_norm": 0.21467560529708862,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4911,
      "step": 155
    },
    {
      "epoch": 0.8221343873517787,
      "grad_norm": 0.203987717628479,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5656,
      "step": 156
    },
    {
      "epoch": 0.8274044795783926,
      "grad_norm": 0.191598042845726,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.467,
      "step": 157
    },
    {
      "epoch": 0.8326745718050066,
      "grad_norm": 0.18605875968933105,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.487,
      "step": 158
    },
    {
      "epoch": 0.8379446640316206,
      "grad_norm": 0.1880578100681305,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.4907,
      "step": 159
    },
    {
      "epoch": 0.8432147562582345,
      "grad_norm": 0.20655931532382965,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.526,
      "step": 160
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.19812270998954773,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.5476,
      "step": 161
    },
    {
      "epoch": 0.8537549407114624,
      "grad_norm": 0.18295344710350037,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.4685,
      "step": 162
    },
    {
      "epoch": 0.8590250329380764,
      "grad_norm": 0.1761408895254135,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4653,
      "step": 163
    },
    {
      "epoch": 0.8642951251646904,
      "grad_norm": 0.18371523916721344,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.4753,
      "step": 164
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.19897453486919403,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.5028,
      "step": 165
    },
    {
      "epoch": 0.8748353096179183,
      "grad_norm": 0.18891547620296478,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.4838,
      "step": 166
    },
    {
      "epoch": 0.8801054018445322,
      "grad_norm": 0.2042507827281952,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.3962,
      "step": 167
    },
    {
      "epoch": 0.8853754940711462,
      "grad_norm": 0.1939568966627121,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.4345,
      "step": 168
    },
    {
      "epoch": 0.8906455862977603,
      "grad_norm": 0.19322411715984344,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.4055,
      "step": 169
    },
    {
      "epoch": 0.8959156785243741,
      "grad_norm": 0.2057853639125824,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.391,
      "step": 170
    },
    {
      "epoch": 0.9011857707509882,
      "grad_norm": 0.21108949184417725,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.4315,
      "step": 171
    },
    {
      "epoch": 0.9064558629776021,
      "grad_norm": 0.22415423393249512,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.3986,
      "step": 172
    },
    {
      "epoch": 0.9117259552042161,
      "grad_norm": 0.2361517697572708,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.4095,
      "step": 173
    },
    {
      "epoch": 0.9169960474308301,
      "grad_norm": 0.22511349618434906,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.3913,
      "step": 174
    },
    {
      "epoch": 0.922266139657444,
      "grad_norm": 0.25515177845954895,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.4075,
      "step": 175
    },
    {
      "epoch": 0.927536231884058,
      "grad_norm": 0.27699339389801025,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3333,
      "step": 176
    },
    {
      "epoch": 0.932806324110672,
      "grad_norm": 0.2925109565258026,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.317,
      "step": 177
    },
    {
      "epoch": 0.9380764163372859,
      "grad_norm": 0.4690416157245636,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.2539,
      "step": 178
    },
    {
      "epoch": 0.9433465085638999,
      "grad_norm": 0.4413660168647766,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0219,
      "step": 179
    },
    {
      "epoch": 0.9486166007905138,
      "grad_norm": 0.037783533334732056,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0025,
      "step": 180
    },
    {
      "epoch": 0.9538866930171278,
      "grad_norm": 0.09441981464624405,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0037,
      "step": 181
    },
    {
      "epoch": 0.9591567852437418,
      "grad_norm": 0.03607313334941864,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0025,
      "step": 182
    },
    {
      "epoch": 0.9644268774703557,
      "grad_norm": 0.43167951703071594,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.012,
      "step": 183
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.29739925265312195,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0115,
      "step": 184
    },
    {
      "epoch": 0.9749670619235836,
      "grad_norm": 0.055825311690568924,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.0029,
      "step": 185
    },
    {
      "epoch": 0.9802371541501976,
      "grad_norm": 0.0430498905479908,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.003,
      "step": 186
    },
    {
      "epoch": 0.9855072463768116,
      "grad_norm": 0.037716783583164215,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0025,
      "step": 187
    },
    {
      "epoch": 0.9907773386034255,
      "grad_norm": 0.00590119045227766,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0003,
      "step": 188
    },
    {
      "epoch": 0.9960474308300395,
      "grad_norm": 0.164833202958107,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.4932,
      "step": 189
    },
    {
      "epoch": 1.0013175230566536,
      "grad_norm": 0.2937326729297638,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.4547,
      "step": 190
    },
    {
      "epoch": 1.0065876152832676,
      "grad_norm": 0.15986718237400055,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.5349,
      "step": 191
    },
    {
      "epoch": 1.0118577075098814,
      "grad_norm": 0.1768161803483963,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.5207,
      "step": 192
    },
    {
      "epoch": 1.0171277997364954,
      "grad_norm": 0.15922577679157257,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.5112,
      "step": 193
    },
    {
      "epoch": 1.0223978919631094,
      "grad_norm": 0.1566813588142395,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.5156,
      "step": 194
    },
    {
      "epoch": 1.0276679841897234,
      "grad_norm": 0.1613328456878662,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.4768,
      "step": 195
    },
    {
      "epoch": 1.0329380764163374,
      "grad_norm": 0.156645268201828,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.484,
      "step": 196
    },
    {
      "epoch": 1.0382081686429512,
      "grad_norm": 0.17111070454120636,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.4594,
      "step": 197
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.1634788066148758,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.4922,
      "step": 198
    },
    {
      "epoch": 1.0487483530961792,
      "grad_norm": 0.1603475958108902,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5023,
      "step": 199
    },
    {
      "epoch": 1.0540184453227932,
      "grad_norm": 0.17399875819683075,
      "learning_rate": 0.0,
      "loss": 0.4998,
      "step": 200
    },
    {
      "epoch": 1.0540184453227932,
      "eval_loss": 0.3519905209541321,
      "eval_runtime": 44.739,
      "eval_samples_per_second": 7.153,
      "eval_steps_per_second": 1.788,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.255509203694387e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}