{
  "best_metric": 0.8628646731376648,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.11114198388441233,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005557099194220616,
      "grad_norm": 0.3096221387386322,
      "learning_rate": 1e-05,
      "loss": 0.6874,
      "step": 1
    },
    {
      "epoch": 0.0011114198388441233,
      "grad_norm": 0.3445380926132202,
      "learning_rate": 2e-05,
      "loss": 0.8533,
      "step": 2
    },
    {
      "epoch": 0.0016671297582661851,
      "grad_norm": 0.38732942938804626,
      "learning_rate": 3e-05,
      "loss": 0.8416,
      "step": 3
    },
    {
      "epoch": 0.0022228396776882466,
      "grad_norm": 0.40373197197914124,
      "learning_rate": 4e-05,
      "loss": 0.9278,
      "step": 4
    },
    {
      "epoch": 0.0027785495971103086,
      "grad_norm": 0.5323252081871033,
      "learning_rate": 5e-05,
      "loss": 0.8707,
      "step": 5
    },
    {
      "epoch": 0.0033342595165323703,
      "grad_norm": 0.40320611000061035,
      "learning_rate": 6e-05,
      "loss": 0.8885,
      "step": 6
    },
    {
      "epoch": 0.003889969435954432,
      "grad_norm": 0.4491368234157562,
      "learning_rate": 7e-05,
      "loss": 0.9183,
      "step": 7
    },
    {
      "epoch": 0.004445679355376493,
      "grad_norm": 0.4458727538585663,
      "learning_rate": 8e-05,
      "loss": 0.8906,
      "step": 8
    },
    {
      "epoch": 0.005001389274798555,
      "grad_norm": 0.48434558510780334,
      "learning_rate": 9e-05,
      "loss": 0.9905,
      "step": 9
    },
    {
      "epoch": 0.005557099194220617,
      "grad_norm": 0.48024508357048035,
      "learning_rate": 0.0001,
      "loss": 0.976,
      "step": 10
    },
    {
      "epoch": 0.006112809113642679,
      "grad_norm": 0.4710797965526581,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8832,
      "step": 11
    },
    {
      "epoch": 0.0066685190330647405,
      "grad_norm": 0.6608445644378662,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8135,
      "step": 12
    },
    {
      "epoch": 0.007224228952486802,
      "grad_norm": 0.7733985185623169,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9128,
      "step": 13
    },
    {
      "epoch": 0.007779938871908864,
      "grad_norm": 0.7563806772232056,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.8965,
      "step": 14
    },
    {
      "epoch": 0.008335648791330925,
      "grad_norm": 0.8561490178108215,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.0446,
      "step": 15
    },
    {
      "epoch": 0.008891358710752986,
      "grad_norm": 0.5314223170280457,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8947,
      "step": 16
    },
    {
      "epoch": 0.009447068630175049,
      "grad_norm": 0.5220498442649841,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9007,
      "step": 17
    },
    {
      "epoch": 0.01000277854959711,
      "grad_norm": 0.4629230499267578,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8739,
      "step": 18
    },
    {
      "epoch": 0.010558488469019172,
      "grad_norm": 0.4347263276576996,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.9759,
      "step": 19
    },
    {
      "epoch": 0.011114198388441235,
      "grad_norm": 0.4404182434082031,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.879,
      "step": 20
    },
    {
      "epoch": 0.011669908307863295,
      "grad_norm": 0.4404293894767761,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9113,
      "step": 21
    },
    {
      "epoch": 0.012225618227285358,
      "grad_norm": 0.5099473595619202,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.9572,
      "step": 22
    },
    {
      "epoch": 0.012781328146707419,
      "grad_norm": 0.49983498454093933,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.9505,
      "step": 23
    },
    {
      "epoch": 0.013337038066129481,
      "grad_norm": 0.45751750469207764,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.9365,
      "step": 24
    },
    {
      "epoch": 0.013892747985551542,
      "grad_norm": 0.4815827012062073,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.9681,
      "step": 25
    },
    {
      "epoch": 0.014448457904973604,
      "grad_norm": 0.49498870968818665,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8768,
      "step": 26
    },
    {
      "epoch": 0.015004167824395665,
      "grad_norm": 0.5356186032295227,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9148,
      "step": 27
    },
    {
      "epoch": 0.015559877743817728,
      "grad_norm": 0.5918698310852051,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.9016,
      "step": 28
    },
    {
      "epoch": 0.01611558766323979,
      "grad_norm": 0.5985519289970398,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9812,
      "step": 29
    },
    {
      "epoch": 0.01667129758266185,
      "grad_norm": 0.6009053587913513,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9144,
      "step": 30
    },
    {
      "epoch": 0.01722700750208391,
      "grad_norm": 0.6077443957328796,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.0156,
      "step": 31
    },
    {
      "epoch": 0.017782717421505972,
      "grad_norm": 0.5306153893470764,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.8645,
      "step": 32
    },
    {
      "epoch": 0.018338427340928037,
      "grad_norm": 0.6579713821411133,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.912,
      "step": 33
    },
    {
      "epoch": 0.018894137260350097,
      "grad_norm": 0.6237910389900208,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.9448,
      "step": 34
    },
    {
      "epoch": 0.019449847179772158,
      "grad_norm": 0.7714456915855408,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.013,
      "step": 35
    },
    {
      "epoch": 0.02000555709919422,
      "grad_norm": 0.8368968367576599,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.0158,
      "step": 36
    },
    {
      "epoch": 0.020561267018616283,
      "grad_norm": 0.7869086265563965,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.9657,
      "step": 37
    },
    {
      "epoch": 0.021116976938038344,
      "grad_norm": 0.868666410446167,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.0059,
      "step": 38
    },
    {
      "epoch": 0.021672686857460405,
      "grad_norm": 0.8402222394943237,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9648,
      "step": 39
    },
    {
      "epoch": 0.02222839677688247,
      "grad_norm": 1.085195779800415,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.914,
      "step": 40
    },
    {
      "epoch": 0.02278410669630453,
      "grad_norm": 1.0071593523025513,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.0821,
      "step": 41
    },
    {
      "epoch": 0.02333981661572659,
      "grad_norm": 0.9272382259368896,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9226,
      "step": 42
    },
    {
      "epoch": 0.02389552653514865,
      "grad_norm": 1.150288701057434,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.9991,
      "step": 43
    },
    {
      "epoch": 0.024451236454570716,
      "grad_norm": 1.181030511856079,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.0868,
      "step": 44
    },
    {
      "epoch": 0.025006946373992776,
      "grad_norm": 1.2696013450622559,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9505,
      "step": 45
    },
    {
      "epoch": 0.025562656293414837,
      "grad_norm": 1.4249521493911743,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.9655,
      "step": 46
    },
    {
      "epoch": 0.026118366212836898,
      "grad_norm": 1.7254620790481567,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.0955,
      "step": 47
    },
    {
      "epoch": 0.026674076132258962,
      "grad_norm": 1.5540577173233032,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.144,
      "step": 48
    },
    {
      "epoch": 0.027229786051681023,
      "grad_norm": 1.849468469619751,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0674,
      "step": 49
    },
    {
      "epoch": 0.027785495971103084,
      "grad_norm": 2.3807289600372314,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.1557,
      "step": 50
    },
    {
      "epoch": 0.027785495971103084,
      "eval_loss": 0.9262280464172363,
      "eval_runtime": 485.2385,
      "eval_samples_per_second": 6.246,
      "eval_steps_per_second": 1.562,
      "step": 50
    },
    {
      "epoch": 0.028341205890525144,
      "grad_norm": 0.6152607798576355,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.6218,
      "step": 51
    },
    {
      "epoch": 0.02889691580994721,
      "grad_norm": 0.6119871735572815,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.7201,
      "step": 52
    },
    {
      "epoch": 0.02945262572936927,
      "grad_norm": 0.6875957250595093,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8161,
      "step": 53
    },
    {
      "epoch": 0.03000833564879133,
      "grad_norm": 0.5192121863365173,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7156,
      "step": 54
    },
    {
      "epoch": 0.03056404556821339,
      "grad_norm": 0.5001811981201172,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7691,
      "step": 55
    },
    {
      "epoch": 0.031119755487635455,
      "grad_norm": 0.44354963302612305,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7391,
      "step": 56
    },
    {
      "epoch": 0.03167546540705751,
      "grad_norm": 0.4128439724445343,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7258,
      "step": 57
    },
    {
      "epoch": 0.03223117532647958,
      "grad_norm": 0.4332227110862732,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8114,
      "step": 58
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 0.49826887249946594,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7566,
      "step": 59
    },
    {
      "epoch": 0.0333425951653237,
      "grad_norm": 0.5935742259025574,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8343,
      "step": 60
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 0.5643736124038696,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.89,
      "step": 61
    },
    {
      "epoch": 0.03445401500416782,
      "grad_norm": 0.46135735511779785,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8583,
      "step": 62
    },
    {
      "epoch": 0.035009724923589884,
      "grad_norm": 0.46768918633461,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.8019,
      "step": 63
    },
    {
      "epoch": 0.035565434843011945,
      "grad_norm": 1.4605656862258911,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9433,
      "step": 64
    },
    {
      "epoch": 0.03612114476243401,
      "grad_norm": 0.643073320388794,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.8167,
      "step": 65
    },
    {
      "epoch": 0.03667685468185607,
      "grad_norm": 0.5446807146072388,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.899,
      "step": 66
    },
    {
      "epoch": 0.037232564601278134,
      "grad_norm": 0.687372624874115,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8572,
      "step": 67
    },
    {
      "epoch": 0.037788274520700195,
      "grad_norm": 0.5308534502983093,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.8851,
      "step": 68
    },
    {
      "epoch": 0.038343984440122256,
      "grad_norm": 0.5406598448753357,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9101,
      "step": 69
    },
    {
      "epoch": 0.038899694359544316,
      "grad_norm": 0.5616788268089294,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.9062,
      "step": 70
    },
    {
      "epoch": 0.03945540427896638,
      "grad_norm": 0.5090973377227783,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.9327,
      "step": 71
    },
    {
      "epoch": 0.04001111419838844,
      "grad_norm": 0.5834062695503235,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.9146,
      "step": 72
    },
    {
      "epoch": 0.040566824117810506,
      "grad_norm": 0.5961350202560425,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.8507,
      "step": 73
    },
    {
      "epoch": 0.041122534037232567,
      "grad_norm": 0.5611476302146912,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9023,
      "step": 74
    },
    {
      "epoch": 0.04167824395665463,
      "grad_norm": 0.5981151461601257,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.9309,
      "step": 75
    },
    {
      "epoch": 0.04223395387607669,
      "grad_norm": 0.6651081442832947,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.8387,
      "step": 76
    },
    {
      "epoch": 0.04278966379549875,
      "grad_norm": 0.5755109190940857,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.9094,
      "step": 77
    },
    {
      "epoch": 0.04334537371492081,
      "grad_norm": 0.6457306742668152,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9344,
      "step": 78
    },
    {
      "epoch": 0.04390108363434287,
      "grad_norm": 0.6681315898895264,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.9146,
      "step": 79
    },
    {
      "epoch": 0.04445679355376494,
      "grad_norm": 0.6412218809127808,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.9006,
      "step": 80
    },
    {
      "epoch": 0.045012503473187,
      "grad_norm": 0.7244966626167297,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.9162,
      "step": 81
    },
    {
      "epoch": 0.04556821339260906,
      "grad_norm": 0.6981307864189148,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.9197,
      "step": 82
    },
    {
      "epoch": 0.04612392331203112,
      "grad_norm": 0.6621314287185669,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8846,
      "step": 83
    },
    {
      "epoch": 0.04667963323145318,
      "grad_norm": 0.6982636451721191,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.9075,
      "step": 84
    },
    {
      "epoch": 0.04723534315087524,
      "grad_norm": 0.8870342373847961,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.8958,
      "step": 85
    },
    {
      "epoch": 0.0477910530702973,
      "grad_norm": 0.7478469610214233,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9219,
      "step": 86
    },
    {
      "epoch": 0.048346762989719363,
      "grad_norm": 0.8852052092552185,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9669,
      "step": 87
    },
    {
      "epoch": 0.04890247290914143,
      "grad_norm": 0.9566718935966492,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.9394,
      "step": 88
    },
    {
      "epoch": 0.04945818282856349,
      "grad_norm": 0.96366947889328,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8851,
      "step": 89
    },
    {
      "epoch": 0.05001389274798555,
      "grad_norm": 1.0311588048934937,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.9561,
      "step": 90
    },
    {
      "epoch": 0.050569602667407614,
      "grad_norm": 1.0592992305755615,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.003,
      "step": 91
    },
    {
      "epoch": 0.051125312586829674,
      "grad_norm": 0.9809575080871582,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0925,
      "step": 92
    },
    {
      "epoch": 0.051681022506251735,
      "grad_norm": 1.1811975240707397,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.0152,
      "step": 93
    },
    {
      "epoch": 0.052236732425673796,
      "grad_norm": 1.2322711944580078,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.0615,
      "step": 94
    },
    {
      "epoch": 0.05279244234509586,
      "grad_norm": 1.2346220016479492,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.9731,
      "step": 95
    },
    {
      "epoch": 0.053348152264517924,
      "grad_norm": 1.3589791059494019,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.071,
      "step": 96
    },
    {
      "epoch": 0.053903862183939985,
      "grad_norm": 1.3197028636932373,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.975,
      "step": 97
    },
    {
      "epoch": 0.054459572103362046,
      "grad_norm": 1.6303969621658325,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0707,
      "step": 98
    },
    {
      "epoch": 0.05501528202278411,
      "grad_norm": 1.7257357835769653,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.0774,
      "step": 99
    },
    {
      "epoch": 0.05557099194220617,
      "grad_norm": 2.2941479682922363,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.2457,
      "step": 100
    },
    {
      "epoch": 0.05557099194220617,
      "eval_loss": 0.8977280855178833,
      "eval_runtime": 485.037,
      "eval_samples_per_second": 6.249,
      "eval_steps_per_second": 1.563,
      "step": 100
    },
    {
      "epoch": 0.05612670186162823,
      "grad_norm": 0.4302062392234802,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.497,
      "step": 101
    },
    {
      "epoch": 0.05668241178105029,
      "grad_norm": 0.5863476991653442,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.6127,
      "step": 102
    },
    {
      "epoch": 0.05723812170047236,
      "grad_norm": 0.6520615816116333,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.7166,
      "step": 103
    },
    {
      "epoch": 0.05779383161989442,
      "grad_norm": 0.6201066374778748,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.6871,
      "step": 104
    },
    {
      "epoch": 0.05834954153931648,
      "grad_norm": 0.6387415528297424,
      "learning_rate": 5e-05,
      "loss": 0.7832,
      "step": 105
    },
    {
      "epoch": 0.05890525145873854,
      "grad_norm": 0.5291295647621155,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7588,
      "step": 106
    },
    {
      "epoch": 0.0594609613781606,
      "grad_norm": 0.5174488425254822,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.7953,
      "step": 107
    },
    {
      "epoch": 0.06001667129758266,
      "grad_norm": 0.5068111419677734,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7733,
      "step": 108
    },
    {
      "epoch": 0.06057238121700472,
      "grad_norm": 0.483059823513031,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.7016,
      "step": 109
    },
    {
      "epoch": 0.06112809113642678,
      "grad_norm": 0.5098429918289185,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8259,
      "step": 110
    },
    {
      "epoch": 0.06168380105584885,
      "grad_norm": 0.48790547251701355,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7469,
      "step": 111
    },
    {
      "epoch": 0.06223951097527091,
      "grad_norm": 0.47628065943717957,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.6838,
      "step": 112
    },
    {
      "epoch": 0.06279522089469297,
      "grad_norm": 0.45170220732688904,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7768,
      "step": 113
    },
    {
      "epoch": 0.06335093081411503,
      "grad_norm": 0.5596415400505066,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.7799,
      "step": 114
    },
    {
      "epoch": 0.06390664073353709,
      "grad_norm": 0.6097323894500732,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.745,
      "step": 115
    },
    {
      "epoch": 0.06446235065295916,
      "grad_norm": 0.6196081042289734,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8016,
      "step": 116
    },
    {
      "epoch": 0.06501806057238121,
      "grad_norm": 0.5493971705436707,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8414,
      "step": 117
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 0.5350998044013977,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8307,
      "step": 118
    },
    {
      "epoch": 0.06612948041122534,
      "grad_norm": 0.5519810318946838,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8961,
      "step": 119
    },
    {
      "epoch": 0.0666851903306474,
      "grad_norm": 0.5195711851119995,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8139,
      "step": 120
    },
    {
      "epoch": 0.06724090025006946,
      "grad_norm": 0.5278419852256775,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.8392,
      "step": 121
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 0.5770994424819946,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.8381,
      "step": 122
    },
    {
      "epoch": 0.06835232008891359,
      "grad_norm": 0.5510872602462769,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.9033,
      "step": 123
    },
    {
      "epoch": 0.06890803000833565,
      "grad_norm": 0.5439556241035461,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8519,
      "step": 124
    },
    {
      "epoch": 0.06946373992775771,
      "grad_norm": 0.6017346978187561,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.9056,
      "step": 125
    },
    {
      "epoch": 0.07001944984717977,
      "grad_norm": 0.5570154786109924,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.8463,
      "step": 126
    },
    {
      "epoch": 0.07057515976660184,
      "grad_norm": 0.5789839029312134,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.8722,
      "step": 127
    },
    {
      "epoch": 0.07113086968602389,
      "grad_norm": 0.615638792514801,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.8581,
      "step": 128
    },
    {
      "epoch": 0.07168657960544596,
      "grad_norm": 0.645267903804779,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.8193,
      "step": 129
    },
    {
      "epoch": 0.07224228952486803,
      "grad_norm": 0.5697069764137268,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7402,
      "step": 130
    },
    {
      "epoch": 0.07279799944429008,
      "grad_norm": 0.7123498916625977,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7547,
      "step": 131
    },
    {
      "epoch": 0.07335370936371215,
      "grad_norm": 0.6562145948410034,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.841,
      "step": 132
    },
    {
      "epoch": 0.0739094192831342,
      "grad_norm": 0.7559430599212646,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8641,
      "step": 133
    },
    {
      "epoch": 0.07446512920255627,
      "grad_norm": 0.7525032162666321,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8629,
      "step": 134
    },
    {
      "epoch": 0.07502083912197832,
      "grad_norm": 0.7517706751823425,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.8493,
      "step": 135
    },
    {
      "epoch": 0.07557654904140039,
      "grad_norm": 0.9117544889450073,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.979,
      "step": 136
    },
    {
      "epoch": 0.07613225896082246,
      "grad_norm": 0.7862403988838196,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.9017,
      "step": 137
    },
    {
      "epoch": 0.07668796888024451,
      "grad_norm": 0.8671106696128845,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.9356,
      "step": 138
    },
    {
      "epoch": 0.07724367879966658,
      "grad_norm": 0.9080340266227722,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.9758,
      "step": 139
    },
    {
      "epoch": 0.07779938871908863,
      "grad_norm": 0.9741995930671692,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.9595,
      "step": 140
    },
    {
      "epoch": 0.0783550986385107,
      "grad_norm": 1.0070784091949463,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.9375,
      "step": 141
    },
    {
      "epoch": 0.07891080855793275,
      "grad_norm": 1.0656945705413818,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.8457,
      "step": 142
    },
    {
      "epoch": 0.07946651847735482,
      "grad_norm": 1.159580111503601,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0,
      "step": 143
    },
    {
      "epoch": 0.08002222839677688,
      "grad_norm": 1.2903732061386108,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.9655,
      "step": 144
    },
    {
      "epoch": 0.08057793831619894,
      "grad_norm": 1.2341926097869873,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.0107,
      "step": 145
    },
    {
      "epoch": 0.08113364823562101,
      "grad_norm": 1.243120789527893,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.9856,
      "step": 146
    },
    {
      "epoch": 0.08168935815504307,
      "grad_norm": 1.4137181043624878,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.8974,
      "step": 147
    },
    {
      "epoch": 0.08224506807446513,
      "grad_norm": 1.4438540935516357,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.0212,
      "step": 148
    },
    {
      "epoch": 0.08280077799388719,
      "grad_norm": 1.699130654335022,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.0967,
      "step": 149
    },
    {
      "epoch": 0.08335648791330925,
      "grad_norm": 2.626094341278076,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.9766,
      "step": 150
    },
    {
      "epoch": 0.08335648791330925,
      "eval_loss": 0.866513729095459,
      "eval_runtime": 483.5807,
      "eval_samples_per_second": 6.268,
      "eval_steps_per_second": 1.567,
      "step": 150
    },
    {
      "epoch": 0.08391219783273131,
      "grad_norm": 0.43071356415748596,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.6212,
      "step": 151
    },
    {
      "epoch": 0.08446790775215338,
      "grad_norm": 0.4564357399940491,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.5791,
      "step": 152
    },
    {
      "epoch": 0.08502361767157544,
      "grad_norm": 0.4825187623500824,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.6476,
      "step": 153
    },
    {
      "epoch": 0.0855793275909975,
      "grad_norm": 0.604847252368927,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.8215,
      "step": 154
    },
    {
      "epoch": 0.08613503751041957,
      "grad_norm": 0.5483651161193848,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7464,
      "step": 155
    },
    {
      "epoch": 0.08669074742984162,
      "grad_norm": 0.5268886089324951,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.8204,
      "step": 156
    },
    {
      "epoch": 0.08724645734926369,
      "grad_norm": 0.5907043218612671,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.7811,
      "step": 157
    },
    {
      "epoch": 0.08780216726868574,
      "grad_norm": 0.5238073468208313,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.7253,
      "step": 158
    },
    {
      "epoch": 0.08835787718810781,
      "grad_norm": 0.5322824716567993,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.7817,
      "step": 159
    },
    {
      "epoch": 0.08891358710752988,
      "grad_norm": 0.515514075756073,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.8549,
      "step": 160
    },
    {
      "epoch": 0.08946929702695193,
      "grad_norm": 0.49722638726234436,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7593,
      "step": 161
    },
    {
      "epoch": 0.090025006946374,
      "grad_norm": 0.4791252911090851,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7211,
      "step": 162
    },
    {
      "epoch": 0.09058071686579605,
      "grad_norm": 0.509143590927124,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7829,
      "step": 163
    },
    {
      "epoch": 0.09113642678521812,
      "grad_norm": 0.5921031832695007,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.7481,
      "step": 164
    },
    {
      "epoch": 0.09169213670464017,
      "grad_norm": 0.6113850474357605,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.7718,
      "step": 165
    },
    {
      "epoch": 0.09224784662406224,
      "grad_norm": 0.6630951762199402,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.8883,
      "step": 166
    },
    {
      "epoch": 0.0928035565434843,
      "grad_norm": 0.6536318063735962,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.8645,
      "step": 167
    },
    {
      "epoch": 0.09335926646290636,
      "grad_norm": 0.5307266712188721,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8854,
      "step": 168
    },
    {
      "epoch": 0.09391497638232843,
      "grad_norm": 0.5809971690177917,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8454,
      "step": 169
    },
    {
      "epoch": 0.09447068630175048,
      "grad_norm": 0.5535210371017456,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7561,
      "step": 170
    },
    {
      "epoch": 0.09502639622117255,
      "grad_norm": 0.5506969690322876,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7905,
      "step": 171
    },
    {
      "epoch": 0.0955821061405946,
      "grad_norm": 0.6618872284889221,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.8784,
      "step": 172
    },
    {
      "epoch": 0.09613781606001667,
      "grad_norm": 0.5788018703460693,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.9002,
      "step": 173
    },
    {
      "epoch": 0.09669352597943873,
      "grad_norm": 0.5524190068244934,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.9219,
      "step": 174
    },
    {
      "epoch": 0.0972492358988608,
      "grad_norm": 0.5713950991630554,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.854,
      "step": 175
    },
    {
      "epoch": 0.09780494581828286,
      "grad_norm": 0.6136912703514099,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.8333,
      "step": 176
    },
    {
      "epoch": 0.09836065573770492,
      "grad_norm": 0.6428893208503723,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.8411,
      "step": 177
    },
    {
      "epoch": 0.09891636565712698,
      "grad_norm": 0.6516892313957214,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.9672,
      "step": 178
    },
    {
      "epoch": 0.09947207557654904,
      "grad_norm": 0.6879913210868835,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.8086,
      "step": 179
    },
    {
      "epoch": 0.1000277854959711,
      "grad_norm": 0.6599001288414001,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.7506,
      "step": 180
    },
    {
      "epoch": 0.10058349541539316,
      "grad_norm": 0.6834718585014343,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.9374,
      "step": 181
    },
    {
      "epoch": 0.10113920533481523,
      "grad_norm": 0.6849175095558167,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.8561,
      "step": 182
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": 0.7637895941734314,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.8923,
      "step": 183
    },
    {
      "epoch": 0.10225062517365935,
      "grad_norm": 0.7412274479866028,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.8883,
      "step": 184
    },
    {
      "epoch": 0.10280633509308142,
      "grad_norm": 0.8586113452911377,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.964,
      "step": 185
    },
    {
      "epoch": 0.10336204501250347,
      "grad_norm": 0.8107852935791016,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.9385,
      "step": 186
    },
    {
      "epoch": 0.10391775493192554,
      "grad_norm": 1.0877127647399902,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.9892,
      "step": 187
    },
    {
      "epoch": 0.10447346485134759,
      "grad_norm": 0.9704486727714539,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.9466,
      "step": 188
    },
    {
      "epoch": 0.10502917477076966,
      "grad_norm": 1.058051347732544,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.9002,
      "step": 189
    },
    {
      "epoch": 0.10558488469019171,
      "grad_norm": 1.0455724000930786,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.936,
      "step": 190
    },
    {
      "epoch": 0.10614059460961378,
      "grad_norm": 1.0386101007461548,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.9007,
      "step": 191
    },
    {
      "epoch": 0.10669630452903585,
      "grad_norm": 1.10919988155365,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.9403,
      "step": 192
    },
    {
      "epoch": 0.1072520144484579,
      "grad_norm": 1.2226141691207886,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.9448,
      "step": 193
    },
    {
      "epoch": 0.10780772436787997,
      "grad_norm": 1.201768159866333,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.9943,
      "step": 194
    },
    {
      "epoch": 0.10836343428730202,
      "grad_norm": 1.2886711359024048,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.9768,
      "step": 195
    },
    {
      "epoch": 0.10891914420672409,
      "grad_norm": 1.3844603300094604,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.0332,
      "step": 196
    },
    {
      "epoch": 0.10947485412614615,
      "grad_norm": 1.5774954557418823,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.0535,
      "step": 197
    },
    {
      "epoch": 0.11003056404556821,
      "grad_norm": 1.778183937072754,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.0084,
      "step": 198
    },
    {
      "epoch": 0.11058627396499028,
      "grad_norm": 1.7170872688293457,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.1168,
      "step": 199
    },
    {
      "epoch": 0.11114198388441233,
      "grad_norm": 2.3412373065948486,
      "learning_rate": 0.0,
      "loss": 1.0962,
      "step": 200
    },
    {
      "epoch": 0.11114198388441233,
      "eval_loss": 0.8628646731376648,
      "eval_runtime": 485.1156,
      "eval_samples_per_second": 6.248,
      "eval_steps_per_second": 1.563,
      "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": 6.820085038369997e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}