{
  "best_metric": 0.3535088896751404,
  "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": 0.3488181531429291,
      "learning_rate": 1e-05,
      "loss": 0.971,
      "step": 1
    },
    {
      "epoch": 0.005270092226613966,
      "eval_loss": 2.119786024093628,
      "eval_runtime": 44.1411,
      "eval_samples_per_second": 7.249,
      "eval_steps_per_second": 1.812,
      "step": 1
    },
    {
      "epoch": 0.010540184453227932,
      "grad_norm": 0.366464763879776,
      "learning_rate": 2e-05,
      "loss": 0.9456,
      "step": 2
    },
    {
      "epoch": 0.015810276679841896,
      "grad_norm": 0.38300439715385437,
      "learning_rate": 3e-05,
      "loss": 0.9817,
      "step": 3
    },
    {
      "epoch": 0.021080368906455864,
      "grad_norm": 0.42603161931037903,
      "learning_rate": 4e-05,
      "loss": 0.9869,
      "step": 4
    },
    {
      "epoch": 0.026350461133069828,
      "grad_norm": 0.43614181876182556,
      "learning_rate": 5e-05,
      "loss": 0.9842,
      "step": 5
    },
    {
      "epoch": 0.03162055335968379,
      "grad_norm": 0.41480982303619385,
      "learning_rate": 6e-05,
      "loss": 0.9245,
      "step": 6
    },
    {
      "epoch": 0.03689064558629776,
      "grad_norm": 0.35271790623664856,
      "learning_rate": 7e-05,
      "loss": 0.8986,
      "step": 7
    },
    {
      "epoch": 0.04216073781291173,
      "grad_norm": 0.33224037289619446,
      "learning_rate": 8e-05,
      "loss": 0.8301,
      "step": 8
    },
    {
      "epoch": 0.04743083003952569,
      "grad_norm": 0.28957563638687134,
      "learning_rate": 9e-05,
      "loss": 0.791,
      "step": 9
    },
    {
      "epoch": 0.052700922266139656,
      "grad_norm": 0.30843502283096313,
      "learning_rate": 0.0001,
      "loss": 0.7052,
      "step": 10
    },
    {
      "epoch": 0.057971014492753624,
      "grad_norm": 0.3144597113132477,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7279,
      "step": 11
    },
    {
      "epoch": 0.06324110671936758,
      "grad_norm": 0.32661348581314087,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6644,
      "step": 12
    },
    {
      "epoch": 0.06851119894598155,
      "grad_norm": 0.306046724319458,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6711,
      "step": 13
    },
    {
      "epoch": 0.07378129117259552,
      "grad_norm": 0.28587502241134644,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7096,
      "step": 14
    },
    {
      "epoch": 0.07905138339920949,
      "grad_norm": 0.28999942541122437,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7025,
      "step": 15
    },
    {
      "epoch": 0.08432147562582346,
      "grad_norm": 0.24909232556819916,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.6476,
      "step": 16
    },
    {
      "epoch": 0.08959156785243742,
      "grad_norm": 0.23373720049858093,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.643,
      "step": 17
    },
    {
      "epoch": 0.09486166007905138,
      "grad_norm": 0.23427610099315643,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.5565,
      "step": 18
    },
    {
      "epoch": 0.10013175230566534,
      "grad_norm": 0.24505065381526947,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6179,
      "step": 19
    },
    {
      "epoch": 0.10540184453227931,
      "grad_norm": 0.25573328137397766,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6069,
      "step": 20
    },
    {
      "epoch": 0.11067193675889328,
      "grad_norm": 0.21897849440574646,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.535,
      "step": 21
    },
    {
      "epoch": 0.11594202898550725,
      "grad_norm": 0.20662955939769745,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.4952,
      "step": 22
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.2481864094734192,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.5663,
      "step": 23
    },
    {
      "epoch": 0.12648221343873517,
      "grad_norm": 0.23671895265579224,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5013,
      "step": 24
    },
    {
      "epoch": 0.13175230566534915,
      "grad_norm": 0.2191077619791031,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4785,
      "step": 25
    },
    {
      "epoch": 0.1370223978919631,
      "grad_norm": 0.23326699435710907,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.5481,
      "step": 26
    },
    {
      "epoch": 0.1422924901185771,
      "grad_norm": 0.23572316765785217,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.5752,
      "step": 27
    },
    {
      "epoch": 0.14756258234519104,
      "grad_norm": 0.21467173099517822,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4919,
      "step": 28
    },
    {
      "epoch": 0.152832674571805,
      "grad_norm": 0.21976681053638458,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4235,
      "step": 29
    },
    {
      "epoch": 0.15810276679841898,
      "grad_norm": 0.19308561086654663,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4498,
      "step": 30
    },
    {
      "epoch": 0.16337285902503293,
      "grad_norm": 0.21107713878154755,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4622,
      "step": 31
    },
    {
      "epoch": 0.1686429512516469,
      "grad_norm": 0.23846441507339478,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.4003,
      "step": 32
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.23483845591545105,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.3773,
      "step": 33
    },
    {
      "epoch": 0.17918313570487485,
      "grad_norm": 0.2150615006685257,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3713,
      "step": 34
    },
    {
      "epoch": 0.1844532279314888,
      "grad_norm": 0.2618648111820221,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.3915,
      "step": 35
    },
    {
      "epoch": 0.18972332015810275,
      "grad_norm": 0.28262847661972046,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.349,
      "step": 36
    },
    {
      "epoch": 0.19499341238471674,
      "grad_norm": 4.440731048583984,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.6129,
      "step": 37
    },
    {
      "epoch": 0.2002635046113307,
      "grad_norm": 22.235776901245117,
      "learning_rate": 9.473646649103818e-05,
      "loss": 8.5355,
      "step": 38
    },
    {
      "epoch": 0.20553359683794467,
      "grad_norm": 10.465611457824707,
      "learning_rate": 9.43611409721806e-05,
      "loss": 5.6968,
      "step": 39
    },
    {
      "epoch": 0.21080368906455862,
      "grad_norm": 7.774234771728516,
      "learning_rate": 9.397368756032445e-05,
      "loss": 4.3296,
      "step": 40
    },
    {
      "epoch": 0.2160737812911726,
      "grad_norm": 5.530091285705566,
      "learning_rate": 9.357421218136386e-05,
      "loss": 3.1652,
      "step": 41
    },
    {
      "epoch": 0.22134387351778656,
      "grad_norm": 3.7415385246276855,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.2838,
      "step": 42
    },
    {
      "epoch": 0.22661396574440051,
      "grad_norm": 4.079122066497803,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.7784,
      "step": 43
    },
    {
      "epoch": 0.2318840579710145,
      "grad_norm": 3.2967798709869385,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.0932,
      "step": 44
    },
    {
      "epoch": 0.23715415019762845,
      "grad_norm": 6.557519435882568,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5749,
      "step": 45
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 1.7553516626358032,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.2181,
      "step": 46
    },
    {
      "epoch": 0.24769433465085638,
      "grad_norm": 6.755886554718018,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.2453,
      "step": 47
    },
    {
      "epoch": 0.25296442687747034,
      "grad_norm": 54.71451187133789,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.3616,
      "step": 48
    },
    {
      "epoch": 0.25823451910408435,
      "grad_norm": 15.011455535888672,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.6128,
      "step": 49
    },
    {
      "epoch": 0.2635046113306983,
      "grad_norm": 4.3047356605529785,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0643,
      "step": 50
    },
    {
      "epoch": 0.2635046113306983,
      "eval_loss": 0.6502147912979126,
      "eval_runtime": 44.9383,
      "eval_samples_per_second": 7.121,
      "eval_steps_per_second": 1.78,
      "step": 50
    },
    {
      "epoch": 0.26877470355731226,
      "grad_norm": 1.4422467947006226,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.8397,
      "step": 51
    },
    {
      "epoch": 0.2740447957839262,
      "grad_norm": 0.6179233193397522,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.6859,
      "step": 52
    },
    {
      "epoch": 0.27931488801054016,
      "grad_norm": 0.39753061532974243,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6438,
      "step": 53
    },
    {
      "epoch": 0.2845849802371542,
      "grad_norm": 0.2857178747653961,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.645,
      "step": 54
    },
    {
      "epoch": 0.2898550724637681,
      "grad_norm": 0.25977158546447754,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6135,
      "step": 55
    },
    {
      "epoch": 0.2951251646903821,
      "grad_norm": 0.263729453086853,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.5791,
      "step": 56
    },
    {
      "epoch": 0.30039525691699603,
      "grad_norm": 0.2634493410587311,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.5738,
      "step": 57
    },
    {
      "epoch": 0.30566534914361,
      "grad_norm": 0.2341052144765854,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5836,
      "step": 58
    },
    {
      "epoch": 0.310935441370224,
      "grad_norm": 0.24500395357608795,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.5745,
      "step": 59
    },
    {
      "epoch": 0.31620553359683795,
      "grad_norm": 0.22350500524044037,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.5422,
      "step": 60
    },
    {
      "epoch": 0.3214756258234519,
      "grad_norm": 0.22490373253822327,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6384,
      "step": 61
    },
    {
      "epoch": 0.32674571805006586,
      "grad_norm": 0.21709252893924713,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5472,
      "step": 62
    },
    {
      "epoch": 0.33201581027667987,
      "grad_norm": 0.2015865594148636,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.542,
      "step": 63
    },
    {
      "epoch": 0.3372859025032938,
      "grad_norm": 0.2102964222431183,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.5385,
      "step": 64
    },
    {
      "epoch": 0.3425559947299078,
      "grad_norm": 0.18773017823696136,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5295,
      "step": 65
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.20135360956192017,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.4902,
      "step": 66
    },
    {
      "epoch": 0.3530961791831357,
      "grad_norm": 0.19054323434829712,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5072,
      "step": 67
    },
    {
      "epoch": 0.3583662714097497,
      "grad_norm": 0.19519297778606415,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.4705,
      "step": 68
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.1892998069524765,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4933,
      "step": 69
    },
    {
      "epoch": 0.3689064558629776,
      "grad_norm": 0.20246605575084686,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.4983,
      "step": 70
    },
    {
      "epoch": 0.37417654808959155,
      "grad_norm": 0.19214019179344177,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.4768,
      "step": 71
    },
    {
      "epoch": 0.3794466403162055,
      "grad_norm": 0.18722325563430786,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4211,
      "step": 72
    },
    {
      "epoch": 0.3847167325428195,
      "grad_norm": 0.19601550698280334,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.4519,
      "step": 73
    },
    {
      "epoch": 0.38998682476943347,
      "grad_norm": 0.19955334067344666,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.429,
      "step": 74
    },
    {
      "epoch": 0.3952569169960474,
      "grad_norm": 0.20580251514911652,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4519,
      "step": 75
    },
    {
      "epoch": 0.4005270092226614,
      "grad_norm": 0.18084149062633514,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.3787,
      "step": 76
    },
    {
      "epoch": 0.4057971014492754,
      "grad_norm": 0.1843647062778473,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.4103,
      "step": 77
    },
    {
      "epoch": 0.41106719367588934,
      "grad_norm": 0.20221984386444092,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.3794,
      "step": 78
    },
    {
      "epoch": 0.4163372859025033,
      "grad_norm": 0.20906153321266174,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.3586,
      "step": 79
    },
    {
      "epoch": 0.42160737812911725,
      "grad_norm": 0.19743655622005463,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4697,
      "step": 80
    },
    {
      "epoch": 0.4268774703557312,
      "grad_norm": 0.20642118155956268,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3716,
      "step": 81
    },
    {
      "epoch": 0.4321475625823452,
      "grad_norm": 0.1994498372077942,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3359,
      "step": 82
    },
    {
      "epoch": 0.43741765480895917,
      "grad_norm": 0.3456531763076782,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.366,
      "step": 83
    },
    {
      "epoch": 0.4426877470355731,
      "grad_norm": 0.2487287074327469,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3729,
      "step": 84
    },
    {
      "epoch": 0.4479578392621871,
      "grad_norm": 0.26895594596862793,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.2886,
      "step": 85
    },
    {
      "epoch": 0.45322793148880103,
      "grad_norm": 6.763861179351807,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.4621,
      "step": 86
    },
    {
      "epoch": 0.45849802371541504,
      "grad_norm": 5.201327323913574,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.0377,
      "step": 87
    },
    {
      "epoch": 0.463768115942029,
      "grad_norm": 3.6956570148468018,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.5751,
      "step": 88
    },
    {
      "epoch": 0.46903820816864294,
      "grad_norm": 2.2494301795959473,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.2912,
      "step": 89
    },
    {
      "epoch": 0.4743083003952569,
      "grad_norm": 1.6042371988296509,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1958,
      "step": 90
    },
    {
      "epoch": 0.4795783926218709,
      "grad_norm": 1.4050320386886597,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.1562,
      "step": 91
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.6471301913261414,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0531,
      "step": 92
    },
    {
      "epoch": 0.4901185770750988,
      "grad_norm": 0.19867514073848724,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.017,
      "step": 93
    },
    {
      "epoch": 0.49538866930171277,
      "grad_norm": 0.7813922166824341,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0213,
      "step": 94
    },
    {
      "epoch": 0.5006587615283268,
      "grad_norm": 0.39590123295783997,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6861,
      "step": 95
    },
    {
      "epoch": 0.5059288537549407,
      "grad_norm": 0.38280797004699707,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.6534,
      "step": 96
    },
    {
      "epoch": 0.5111989459815547,
      "grad_norm": 0.28967928886413574,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.5774,
      "step": 97
    },
    {
      "epoch": 0.5164690382081687,
      "grad_norm": 0.23634879291057587,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5416,
      "step": 98
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.22649812698364258,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5984,
      "step": 99
    },
    {
      "epoch": 0.5270092226613966,
      "grad_norm": 0.19956818222999573,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5219,
      "step": 100
    },
    {
      "epoch": 0.5270092226613966,
      "eval_loss": 0.4019997715950012,
      "eval_runtime": 44.9271,
      "eval_samples_per_second": 7.123,
      "eval_steps_per_second": 1.781,
      "step": 100
    },
    {
      "epoch": 0.5322793148880105,
      "grad_norm": 0.1942063570022583,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.5314,
      "step": 101
    },
    {
      "epoch": 0.5375494071146245,
      "grad_norm": 0.20653952658176422,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5695,
      "step": 102
    },
    {
      "epoch": 0.5428194993412385,
      "grad_norm": 0.21895094215869904,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5594,
      "step": 103
    },
    {
      "epoch": 0.5480895915678524,
      "grad_norm": 0.21609008312225342,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5102,
      "step": 104
    },
    {
      "epoch": 0.5533596837944664,
      "grad_norm": 0.19574272632598877,
      "learning_rate": 5e-05,
      "loss": 0.5271,
      "step": 105
    },
    {
      "epoch": 0.5586297760210803,
      "grad_norm": 0.1909104436635971,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.5769,
      "step": 106
    },
    {
      "epoch": 0.5638998682476943,
      "grad_norm": 0.18439921736717224,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.5635,
      "step": 107
    },
    {
      "epoch": 0.5691699604743083,
      "grad_norm": 0.18986089527606964,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.4907,
      "step": 108
    },
    {
      "epoch": 0.5744400527009222,
      "grad_norm": 0.22741711139678955,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.5497,
      "step": 109
    },
    {
      "epoch": 0.5797101449275363,
      "grad_norm": 0.2027551382780075,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.5333,
      "step": 110
    },
    {
      "epoch": 0.5849802371541502,
      "grad_norm": 0.20353972911834717,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5304,
      "step": 111
    },
    {
      "epoch": 0.5902503293807642,
      "grad_norm": 0.19898013770580292,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.4808,
      "step": 112
    },
    {
      "epoch": 0.5955204216073782,
      "grad_norm": 0.18878135085105896,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.4775,
      "step": 113
    },
    {
      "epoch": 0.6007905138339921,
      "grad_norm": 0.20128917694091797,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.5381,
      "step": 114
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.20815399289131165,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.5188,
      "step": 115
    },
    {
      "epoch": 0.61133069828722,
      "grad_norm": 0.20932593941688538,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5169,
      "step": 116
    },
    {
      "epoch": 0.616600790513834,
      "grad_norm": 0.19482028484344482,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4818,
      "step": 117
    },
    {
      "epoch": 0.621870882740448,
      "grad_norm": 0.20733366906642914,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.5289,
      "step": 118
    },
    {
      "epoch": 0.6271409749670619,
      "grad_norm": 0.2151653915643692,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.4591,
      "step": 119
    },
    {
      "epoch": 0.6324110671936759,
      "grad_norm": 0.20599502325057983,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.4238,
      "step": 120
    },
    {
      "epoch": 0.6376811594202898,
      "grad_norm": 0.19534289836883545,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.4496,
      "step": 121
    },
    {
      "epoch": 0.6429512516469038,
      "grad_norm": 0.20112793147563934,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.4554,
      "step": 122
    },
    {
      "epoch": 0.6482213438735178,
      "grad_norm": 0.2071412354707718,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.4623,
      "step": 123
    },
    {
      "epoch": 0.6534914361001317,
      "grad_norm": 0.20483915507793427,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.4491,
      "step": 124
    },
    {
      "epoch": 0.6587615283267457,
      "grad_norm": 0.20107446610927582,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4301,
      "step": 125
    },
    {
      "epoch": 0.6640316205533597,
      "grad_norm": 0.1856612116098404,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3408,
      "step": 126
    },
    {
      "epoch": 0.6693017127799736,
      "grad_norm": 0.20273374021053314,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.3855,
      "step": 127
    },
    {
      "epoch": 0.6745718050065876,
      "grad_norm": 0.19537442922592163,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.379,
      "step": 128
    },
    {
      "epoch": 0.6798418972332015,
      "grad_norm": 0.20136794447898865,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3387,
      "step": 129
    },
    {
      "epoch": 0.6851119894598156,
      "grad_norm": 0.20087219774723053,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.2729,
      "step": 130
    },
    {
      "epoch": 0.6903820816864296,
      "grad_norm": 0.26547491550445557,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.2865,
      "step": 131
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 4.373338222503662,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.4488,
      "step": 132
    },
    {
      "epoch": 0.7009222661396575,
      "grad_norm": 3.9838695526123047,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.3726,
      "step": 133
    },
    {
      "epoch": 0.7061923583662714,
      "grad_norm": 3.346055507659912,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.2625,
      "step": 134
    },
    {
      "epoch": 0.7114624505928854,
      "grad_norm": 1.9495670795440674,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.1323,
      "step": 135
    },
    {
      "epoch": 0.7167325428194994,
      "grad_norm": 0.8990634083747864,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0567,
      "step": 136
    },
    {
      "epoch": 0.7220026350461133,
      "grad_norm": 0.3868858218193054,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0235,
      "step": 137
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.20018455386161804,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0126,
      "step": 138
    },
    {
      "epoch": 0.7325428194993412,
      "grad_norm": 0.16753485798835754,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0096,
      "step": 139
    },
    {
      "epoch": 0.7378129117259552,
      "grad_norm": 0.08104085177183151,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0049,
      "step": 140
    },
    {
      "epoch": 0.7430830039525692,
      "grad_norm": 0.6239838004112244,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0156,
      "step": 141
    },
    {
      "epoch": 0.7483530961791831,
      "grad_norm": 0.23692312836647034,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6055,
      "step": 142
    },
    {
      "epoch": 0.7536231884057971,
      "grad_norm": 0.21514175832271576,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.519,
      "step": 143
    },
    {
      "epoch": 0.758893280632411,
      "grad_norm": 0.216633602976799,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5203,
      "step": 144
    },
    {
      "epoch": 0.764163372859025,
      "grad_norm": 0.18934868276119232,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.5504,
      "step": 145
    },
    {
      "epoch": 0.769433465085639,
      "grad_norm": 0.20502689480781555,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5077,
      "step": 146
    },
    {
      "epoch": 0.7747035573122529,
      "grad_norm": 0.1809558868408203,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.4962,
      "step": 147
    },
    {
      "epoch": 0.7799736495388669,
      "grad_norm": 0.1955443173646927,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5277,
      "step": 148
    },
    {
      "epoch": 0.7852437417654808,
      "grad_norm": 0.17776170372962952,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5526,
      "step": 149
    },
    {
      "epoch": 0.7905138339920948,
      "grad_norm": 0.16883736848831177,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.4724,
      "step": 150
    },
    {
      "epoch": 0.7905138339920948,
      "eval_loss": 0.3691774010658264,
      "eval_runtime": 44.9439,
      "eval_samples_per_second": 7.12,
      "eval_steps_per_second": 1.78,
      "step": 150
    },
    {
      "epoch": 0.7957839262187089,
      "grad_norm": 0.17091117799282074,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5482,
      "step": 151
    },
    {
      "epoch": 0.8010540184453228,
      "grad_norm": 0.18619947135448456,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4994,
      "step": 152
    },
    {
      "epoch": 0.8063241106719368,
      "grad_norm": 0.1886468380689621,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5155,
      "step": 153
    },
    {
      "epoch": 0.8115942028985508,
      "grad_norm": 0.1914134919643402,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.4792,
      "step": 154
    },
    {
      "epoch": 0.8168642951251647,
      "grad_norm": 0.20857392251491547,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.492,
      "step": 155
    },
    {
      "epoch": 0.8221343873517787,
      "grad_norm": 0.2020442932844162,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5672,
      "step": 156
    },
    {
      "epoch": 0.8274044795783926,
      "grad_norm": 0.18997247517108917,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.4684,
      "step": 157
    },
    {
      "epoch": 0.8326745718050066,
      "grad_norm": 0.18641631305217743,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.4868,
      "step": 158
    },
    {
      "epoch": 0.8379446640316206,
      "grad_norm": 0.1892530769109726,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.4924,
      "step": 159
    },
    {
      "epoch": 0.8432147562582345,
      "grad_norm": 0.20645610988140106,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.5269,
      "step": 160
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.20020997524261475,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.551,
      "step": 161
    },
    {
      "epoch": 0.8537549407114624,
      "grad_norm": 0.18515610694885254,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.4702,
      "step": 162
    },
    {
      "epoch": 0.8590250329380764,
      "grad_norm": 0.17843441665172577,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4678,
      "step": 163
    },
    {
      "epoch": 0.8642951251646904,
      "grad_norm": 0.1874718815088272,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.4779,
      "step": 164
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.20329120755195618,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.5052,
      "step": 165
    },
    {
      "epoch": 0.8748353096179183,
      "grad_norm": 0.19417767226696014,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.4871,
      "step": 166
    },
    {
      "epoch": 0.8801054018445322,
      "grad_norm": 0.20903795957565308,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.3998,
      "step": 167
    },
    {
      "epoch": 0.8853754940711462,
      "grad_norm": 0.19657038152217865,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.4375,
      "step": 168
    },
    {
      "epoch": 0.8906455862977603,
      "grad_norm": 0.1960580199956894,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.4075,
      "step": 169
    },
    {
      "epoch": 0.8959156785243741,
      "grad_norm": 0.20963042974472046,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.3941,
      "step": 170
    },
    {
      "epoch": 0.9011857707509882,
      "grad_norm": 0.21628618240356445,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.4352,
      "step": 171
    },
    {
      "epoch": 0.9064558629776021,
      "grad_norm": 0.2309342622756958,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.4025,
      "step": 172
    },
    {
      "epoch": 0.9117259552042161,
      "grad_norm": 0.23900370299816132,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.4133,
      "step": 173
    },
    {
      "epoch": 0.9169960474308301,
      "grad_norm": 0.23021411895751953,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.394,
      "step": 174
    },
    {
      "epoch": 0.922266139657444,
      "grad_norm": 0.2580454647541046,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.408,
      "step": 175
    },
    {
      "epoch": 0.927536231884058,
      "grad_norm": 0.2824423015117645,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3359,
      "step": 176
    },
    {
      "epoch": 0.932806324110672,
      "grad_norm": 0.3019857406616211,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.3194,
      "step": 177
    },
    {
      "epoch": 0.9380764163372859,
      "grad_norm": 0.47824108600616455,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.2572,
      "step": 178
    },
    {
      "epoch": 0.9433465085638999,
      "grad_norm": 0.2725706398487091,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0127,
      "step": 179
    },
    {
      "epoch": 0.9486166007905138,
      "grad_norm": 0.032354071736335754,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.002,
      "step": 180
    },
    {
      "epoch": 0.9538866930171278,
      "grad_norm": 0.0349271260201931,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0022,
      "step": 181
    },
    {
      "epoch": 0.9591567852437418,
      "grad_norm": 0.03415447846055031,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0027,
      "step": 182
    },
    {
      "epoch": 0.9644268774703557,
      "grad_norm": 0.03492279350757599,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.002,
      "step": 183
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.02771613374352455,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0018,
      "step": 184
    },
    {
      "epoch": 0.9749670619235836,
      "grad_norm": 0.031478945165872574,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.0019,
      "step": 185
    },
    {
      "epoch": 0.9802371541501976,
      "grad_norm": 0.033723048865795135,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0022,
      "step": 186
    },
    {
      "epoch": 0.9855072463768116,
      "grad_norm": 0.029208460822701454,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.002,
      "step": 187
    },
    {
      "epoch": 0.9907773386034255,
      "grad_norm": 0.015320814214646816,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0006,
      "step": 188
    },
    {
      "epoch": 0.9960474308300395,
      "grad_norm": 0.1652088463306427,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.4945,
      "step": 189
    },
    {
      "epoch": 1.0013175230566536,
      "grad_norm": 0.2972957193851471,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.4545,
      "step": 190
    },
    {
      "epoch": 1.0065876152832676,
      "grad_norm": 0.15943707525730133,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.5378,
      "step": 191
    },
    {
      "epoch": 1.0118577075098814,
      "grad_norm": 0.1754513829946518,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.5254,
      "step": 192
    },
    {
      "epoch": 1.0171277997364954,
      "grad_norm": 0.15796075761318207,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.5138,
      "step": 193
    },
    {
      "epoch": 1.0223978919631094,
      "grad_norm": 0.1577950119972229,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.519,
      "step": 194
    },
    {
      "epoch": 1.0276679841897234,
      "grad_norm": 0.15898647904396057,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.4792,
      "step": 195
    },
    {
      "epoch": 1.0329380764163374,
      "grad_norm": 0.15776436030864716,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.4871,
      "step": 196
    },
    {
      "epoch": 1.0382081686429512,
      "grad_norm": 0.16818857192993164,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.4613,
      "step": 197
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.16440455615520477,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.4949,
      "step": 198
    },
    {
      "epoch": 1.0487483530961792,
      "grad_norm": 0.15880745649337769,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5041,
      "step": 199
    },
    {
      "epoch": 1.0540184453227932,
      "grad_norm": 0.17143286764621735,
      "learning_rate": 0.0,
      "loss": 0.5015,
      "step": 200
    },
    {
      "epoch": 1.0540184453227932,
      "eval_loss": 0.3535088896751404,
      "eval_runtime": 44.9252,
      "eval_samples_per_second": 7.123,
      "eval_steps_per_second": 1.781,
      "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
}