{
  "best_metric": 2.4489593505859375,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.39603960396039606,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019801980198019802,
      "grad_norm": 0.740184485912323,
      "learning_rate": 1e-05,
      "loss": 2.4112,
      "step": 1
    },
    {
      "epoch": 0.0019801980198019802,
      "eval_loss": 2.6863114833831787,
      "eval_runtime": 17.4613,
      "eval_samples_per_second": 48.736,
      "eval_steps_per_second": 12.198,
      "step": 1
    },
    {
      "epoch": 0.0039603960396039604,
      "grad_norm": 0.8854779005050659,
      "learning_rate": 2e-05,
      "loss": 2.511,
      "step": 2
    },
    {
      "epoch": 0.005940594059405941,
      "grad_norm": 0.9378243088722229,
      "learning_rate": 3e-05,
      "loss": 2.5368,
      "step": 3
    },
    {
      "epoch": 0.007920792079207921,
      "grad_norm": 0.8493816256523132,
      "learning_rate": 4e-05,
      "loss": 2.4076,
      "step": 4
    },
    {
      "epoch": 0.009900990099009901,
      "grad_norm": 1.0355074405670166,
      "learning_rate": 5e-05,
      "loss": 2.5698,
      "step": 5
    },
    {
      "epoch": 0.011881188118811881,
      "grad_norm": 0.9869332313537598,
      "learning_rate": 6e-05,
      "loss": 2.4832,
      "step": 6
    },
    {
      "epoch": 0.013861386138613862,
      "grad_norm": 0.8589983582496643,
      "learning_rate": 7e-05,
      "loss": 2.401,
      "step": 7
    },
    {
      "epoch": 0.015841584158415842,
      "grad_norm": 0.5886814594268799,
      "learning_rate": 8e-05,
      "loss": 2.4778,
      "step": 8
    },
    {
      "epoch": 0.01782178217821782,
      "grad_norm": 0.5653163194656372,
      "learning_rate": 9e-05,
      "loss": 2.4636,
      "step": 9
    },
    {
      "epoch": 0.019801980198019802,
      "grad_norm": 0.6337383985519409,
      "learning_rate": 0.0001,
      "loss": 2.6002,
      "step": 10
    },
    {
      "epoch": 0.02178217821782178,
      "grad_norm": 0.6765571236610413,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.3673,
      "step": 11
    },
    {
      "epoch": 0.023762376237623763,
      "grad_norm": 0.5764917731285095,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.4456,
      "step": 12
    },
    {
      "epoch": 0.02574257425742574,
      "grad_norm": 0.5215210318565369,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.4409,
      "step": 13
    },
    {
      "epoch": 0.027722772277227723,
      "grad_norm": 0.5955678820610046,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.4795,
      "step": 14
    },
    {
      "epoch": 0.0297029702970297,
      "grad_norm": 0.5137306451797485,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.3785,
      "step": 15
    },
    {
      "epoch": 0.031683168316831684,
      "grad_norm": 0.6253388524055481,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.4408,
      "step": 16
    },
    {
      "epoch": 0.033663366336633666,
      "grad_norm": 0.4909169375896454,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.4155,
      "step": 17
    },
    {
      "epoch": 0.03564356435643564,
      "grad_norm": 0.5244534015655518,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.3945,
      "step": 18
    },
    {
      "epoch": 0.03762376237623762,
      "grad_norm": 0.5957537293434143,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.4523,
      "step": 19
    },
    {
      "epoch": 0.039603960396039604,
      "grad_norm": 0.5087384581565857,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.3346,
      "step": 20
    },
    {
      "epoch": 0.041584158415841586,
      "grad_norm": 0.5359100103378296,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.5601,
      "step": 21
    },
    {
      "epoch": 0.04356435643564356,
      "grad_norm": 0.5234025120735168,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.5496,
      "step": 22
    },
    {
      "epoch": 0.04554455445544554,
      "grad_norm": 0.5566084980964661,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.4211,
      "step": 23
    },
    {
      "epoch": 0.047524752475247525,
      "grad_norm": 0.5281561017036438,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.5104,
      "step": 24
    },
    {
      "epoch": 0.04950495049504951,
      "grad_norm": 0.5216585993766785,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.4064,
      "step": 25
    },
    {
      "epoch": 0.05148514851485148,
      "grad_norm": 0.5333540439605713,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.3945,
      "step": 26
    },
    {
      "epoch": 0.053465346534653464,
      "grad_norm": 0.5435747504234314,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.4617,
      "step": 27
    },
    {
      "epoch": 0.055445544554455446,
      "grad_norm": 0.5713522434234619,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.4444,
      "step": 28
    },
    {
      "epoch": 0.05742574257425743,
      "grad_norm": 0.6960932612419128,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.3573,
      "step": 29
    },
    {
      "epoch": 0.0594059405940594,
      "grad_norm": 0.5823285579681396,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.4597,
      "step": 30
    },
    {
      "epoch": 0.061386138613861385,
      "grad_norm": 0.6012002825737,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.4525,
      "step": 31
    },
    {
      "epoch": 0.06336633663366337,
      "grad_norm": 0.5959309339523315,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.4353,
      "step": 32
    },
    {
      "epoch": 0.06534653465346535,
      "grad_norm": 0.8223351836204529,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.5605,
      "step": 33
    },
    {
      "epoch": 0.06732673267326733,
      "grad_norm": 0.6268564462661743,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.3359,
      "step": 34
    },
    {
      "epoch": 0.06930693069306931,
      "grad_norm": 0.6801354289054871,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.4563,
      "step": 35
    },
    {
      "epoch": 0.07128712871287128,
      "grad_norm": 0.6463386416435242,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.4847,
      "step": 36
    },
    {
      "epoch": 0.07326732673267326,
      "grad_norm": 0.6860770583152771,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.4612,
      "step": 37
    },
    {
      "epoch": 0.07524752475247524,
      "grad_norm": 0.7123834490776062,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.5018,
      "step": 38
    },
    {
      "epoch": 0.07722772277227723,
      "grad_norm": 0.7389307618141174,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.5303,
      "step": 39
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 0.7158656716346741,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.5304,
      "step": 40
    },
    {
      "epoch": 0.08118811881188119,
      "grad_norm": 0.7471336126327515,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.4929,
      "step": 41
    },
    {
      "epoch": 0.08316831683168317,
      "grad_norm": 0.7759936451911926,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.4153,
      "step": 42
    },
    {
      "epoch": 0.08514851485148515,
      "grad_norm": 0.9649326205253601,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.4985,
      "step": 43
    },
    {
      "epoch": 0.08712871287128712,
      "grad_norm": 0.8492192029953003,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.492,
      "step": 44
    },
    {
      "epoch": 0.0891089108910891,
      "grad_norm": 0.8423669338226318,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.6034,
      "step": 45
    },
    {
      "epoch": 0.09108910891089109,
      "grad_norm": 1.0074955224990845,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.6284,
      "step": 46
    },
    {
      "epoch": 0.09306930693069307,
      "grad_norm": 1.0744684934616089,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.5214,
      "step": 47
    },
    {
      "epoch": 0.09504950495049505,
      "grad_norm": 1.1677765846252441,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.766,
      "step": 48
    },
    {
      "epoch": 0.09702970297029703,
      "grad_norm": 1.2065280675888062,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.5692,
      "step": 49
    },
    {
      "epoch": 0.09900990099009901,
      "grad_norm": 2.2678771018981934,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.6882,
      "step": 50
    },
    {
      "epoch": 0.09900990099009901,
      "eval_loss": 2.6347908973693848,
      "eval_runtime": 17.5267,
      "eval_samples_per_second": 48.554,
      "eval_steps_per_second": 12.153,
      "step": 50
    },
    {
      "epoch": 0.100990099009901,
      "grad_norm": 3.0091025829315186,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.5263,
      "step": 51
    },
    {
      "epoch": 0.10297029702970296,
      "grad_norm": 2.5911030769348145,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.4446,
      "step": 52
    },
    {
      "epoch": 0.10495049504950495,
      "grad_norm": 2.032653570175171,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.5393,
      "step": 53
    },
    {
      "epoch": 0.10693069306930693,
      "grad_norm": 1.3425925970077515,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.4587,
      "step": 54
    },
    {
      "epoch": 0.10891089108910891,
      "grad_norm": 0.7180945873260498,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.4167,
      "step": 55
    },
    {
      "epoch": 0.11089108910891089,
      "grad_norm": 0.4491579234600067,
      "learning_rate": 8.622126023955446e-05,
      "loss": 2.4759,
      "step": 56
    },
    {
      "epoch": 0.11287128712871287,
      "grad_norm": 0.4148993194103241,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.358,
      "step": 57
    },
    {
      "epoch": 0.11485148514851486,
      "grad_norm": 0.3795308470726013,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.3737,
      "step": 58
    },
    {
      "epoch": 0.11683168316831684,
      "grad_norm": 0.3720359802246094,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.3098,
      "step": 59
    },
    {
      "epoch": 0.1188118811881188,
      "grad_norm": 0.39235377311706543,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.4268,
      "step": 60
    },
    {
      "epoch": 0.12079207920792079,
      "grad_norm": 0.40234073996543884,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.3345,
      "step": 61
    },
    {
      "epoch": 0.12277227722772277,
      "grad_norm": 0.4109947681427002,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.46,
      "step": 62
    },
    {
      "epoch": 0.12475247524752475,
      "grad_norm": 0.4068487584590912,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.3738,
      "step": 63
    },
    {
      "epoch": 0.12673267326732673,
      "grad_norm": 0.39186495542526245,
      "learning_rate": 8.135881792367686e-05,
      "loss": 2.3968,
      "step": 64
    },
    {
      "epoch": 0.12871287128712872,
      "grad_norm": 0.40950897336006165,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.4378,
      "step": 65
    },
    {
      "epoch": 0.1306930693069307,
      "grad_norm": 0.4007221758365631,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.3862,
      "step": 66
    },
    {
      "epoch": 0.13267326732673268,
      "grad_norm": 0.41376572847366333,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.4285,
      "step": 67
    },
    {
      "epoch": 0.13465346534653466,
      "grad_norm": 0.41112542152404785,
      "learning_rate": 7.871643313414718e-05,
      "loss": 2.517,
      "step": 68
    },
    {
      "epoch": 0.13663366336633664,
      "grad_norm": 0.4579215943813324,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.3708,
      "step": 69
    },
    {
      "epoch": 0.13861386138613863,
      "grad_norm": 0.431108295917511,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.4168,
      "step": 70
    },
    {
      "epoch": 0.1405940594059406,
      "grad_norm": 0.42973315715789795,
      "learning_rate": 7.66515864363997e-05,
      "loss": 2.4979,
      "step": 71
    },
    {
      "epoch": 0.14257425742574256,
      "grad_norm": 0.44449689984321594,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.4562,
      "step": 72
    },
    {
      "epoch": 0.14455445544554454,
      "grad_norm": 0.4433273673057556,
      "learning_rate": 7.52382768867422e-05,
      "loss": 2.4481,
      "step": 73
    },
    {
      "epoch": 0.14653465346534653,
      "grad_norm": 0.4581921398639679,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.4801,
      "step": 74
    },
    {
      "epoch": 0.1485148514851485,
      "grad_norm": 0.4564491808414459,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.4362,
      "step": 75
    },
    {
      "epoch": 0.1504950495049505,
      "grad_norm": 0.4512006342411041,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.4825,
      "step": 76
    },
    {
      "epoch": 0.15247524752475247,
      "grad_norm": 0.49259135127067566,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.4237,
      "step": 77
    },
    {
      "epoch": 0.15445544554455445,
      "grad_norm": 0.4646151661872864,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.4271,
      "step": 78
    },
    {
      "epoch": 0.15643564356435644,
      "grad_norm": 0.49332305788993835,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.476,
      "step": 79
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 0.49859699606895447,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.4939,
      "step": 80
    },
    {
      "epoch": 0.1603960396039604,
      "grad_norm": 0.5360106825828552,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.4622,
      "step": 81
    },
    {
      "epoch": 0.16237623762376238,
      "grad_norm": 0.5232015252113342,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.3833,
      "step": 82
    },
    {
      "epoch": 0.16435643564356436,
      "grad_norm": 0.5606503486633301,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.5818,
      "step": 83
    },
    {
      "epoch": 0.16633663366336635,
      "grad_norm": 0.5686036348342896,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.3171,
      "step": 84
    },
    {
      "epoch": 0.16831683168316833,
      "grad_norm": 0.5630202293395996,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.5338,
      "step": 85
    },
    {
      "epoch": 0.1702970297029703,
      "grad_norm": 0.5604642629623413,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.5086,
      "step": 86
    },
    {
      "epoch": 0.17227722772277226,
      "grad_norm": 0.6153882741928101,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.5925,
      "step": 87
    },
    {
      "epoch": 0.17425742574257425,
      "grad_norm": 0.5997647047042847,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.3646,
      "step": 88
    },
    {
      "epoch": 0.17623762376237623,
      "grad_norm": 0.6267396807670593,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.504,
      "step": 89
    },
    {
      "epoch": 0.1782178217821782,
      "grad_norm": 0.6957364678382874,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.4873,
      "step": 90
    },
    {
      "epoch": 0.1801980198019802,
      "grad_norm": 0.6636099219322205,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.6616,
      "step": 91
    },
    {
      "epoch": 0.18217821782178217,
      "grad_norm": 0.6893649101257324,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.558,
      "step": 92
    },
    {
      "epoch": 0.18415841584158416,
      "grad_norm": 0.6587708592414856,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.4511,
      "step": 93
    },
    {
      "epoch": 0.18613861386138614,
      "grad_norm": 0.7910763025283813,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.4364,
      "step": 94
    },
    {
      "epoch": 0.18811881188118812,
      "grad_norm": 0.8297787308692932,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.5862,
      "step": 95
    },
    {
      "epoch": 0.1900990099009901,
      "grad_norm": 0.933093249797821,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.5867,
      "step": 96
    },
    {
      "epoch": 0.19207920792079208,
      "grad_norm": 0.9696834683418274,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.4786,
      "step": 97
    },
    {
      "epoch": 0.19405940594059407,
      "grad_norm": 1.1176578998565674,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.4409,
      "step": 98
    },
    {
      "epoch": 0.19603960396039605,
      "grad_norm": 1.2134913206100464,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.544,
      "step": 99
    },
    {
      "epoch": 0.19801980198019803,
      "grad_norm": 1.9900872707366943,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.8078,
      "step": 100
    },
    {
      "epoch": 0.19801980198019803,
      "eval_loss": 2.499460458755493,
      "eval_runtime": 17.5135,
      "eval_samples_per_second": 48.591,
      "eval_steps_per_second": 12.162,
      "step": 100
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.901371419429779,
      "learning_rate": 5.330452921628497e-05,
      "loss": 2.3071,
      "step": 101
    },
    {
      "epoch": 0.201980198019802,
      "grad_norm": 0.9919115304946899,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.3717,
      "step": 102
    },
    {
      "epoch": 0.20396039603960395,
      "grad_norm": 1.0072884559631348,
      "learning_rate": 5.165316846586541e-05,
      "loss": 2.3027,
      "step": 103
    },
    {
      "epoch": 0.20594059405940593,
      "grad_norm": 0.7765918374061584,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 2.4297,
      "step": 104
    },
    {
      "epoch": 0.2079207920792079,
      "grad_norm": 0.5551130771636963,
      "learning_rate": 5e-05,
      "loss": 2.2676,
      "step": 105
    },
    {
      "epoch": 0.2099009900990099,
      "grad_norm": 0.3800651729106903,
      "learning_rate": 4.917330276168208e-05,
      "loss": 2.3275,
      "step": 106
    },
    {
      "epoch": 0.21188118811881188,
      "grad_norm": 0.3195657730102539,
      "learning_rate": 4.834683153413459e-05,
      "loss": 2.367,
      "step": 107
    },
    {
      "epoch": 0.21386138613861386,
      "grad_norm": 0.32509028911590576,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.4605,
      "step": 108
    },
    {
      "epoch": 0.21584158415841584,
      "grad_norm": 0.33759263157844543,
      "learning_rate": 4.669547078371504e-05,
      "loss": 2.3787,
      "step": 109
    },
    {
      "epoch": 0.21782178217821782,
      "grad_norm": 0.3417530357837677,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.311,
      "step": 110
    },
    {
      "epoch": 0.2198019801980198,
      "grad_norm": 0.37259143590927124,
      "learning_rate": 4.504772348747687e-05,
      "loss": 2.3761,
      "step": 111
    },
    {
      "epoch": 0.22178217821782178,
      "grad_norm": 0.3790714144706726,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 2.3074,
      "step": 112
    },
    {
      "epoch": 0.22376237623762377,
      "grad_norm": 0.4194207191467285,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 2.3937,
      "step": 113
    },
    {
      "epoch": 0.22574257425742575,
      "grad_norm": 0.3982987403869629,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 2.3951,
      "step": 114
    },
    {
      "epoch": 0.22772277227722773,
      "grad_norm": 0.39006689190864563,
      "learning_rate": 4.17702704859633e-05,
      "loss": 2.3178,
      "step": 115
    },
    {
      "epoch": 0.2297029702970297,
      "grad_norm": 0.40694794058799744,
      "learning_rate": 4.095597328339452e-05,
      "loss": 2.311,
      "step": 116
    },
    {
      "epoch": 0.2316831683168317,
      "grad_norm": 0.40782585740089417,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 2.5222,
      "step": 117
    },
    {
      "epoch": 0.23366336633663368,
      "grad_norm": 0.4021328091621399,
      "learning_rate": 3.933501846281267e-05,
      "loss": 2.332,
      "step": 118
    },
    {
      "epoch": 0.23564356435643563,
      "grad_norm": 0.43970558047294617,
      "learning_rate": 3.852880399766243e-05,
      "loss": 2.517,
      "step": 119
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 0.4378672242164612,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.4108,
      "step": 120
    },
    {
      "epoch": 0.2396039603960396,
      "grad_norm": 0.4263209402561188,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 2.3732,
      "step": 121
    },
    {
      "epoch": 0.24158415841584158,
      "grad_norm": 0.44349074363708496,
      "learning_rate": 3.612985456190778e-05,
      "loss": 2.3798,
      "step": 122
    },
    {
      "epoch": 0.24356435643564356,
      "grad_norm": 0.456597238779068,
      "learning_rate": 3.533749813077677e-05,
      "loss": 2.4424,
      "step": 123
    },
    {
      "epoch": 0.24554455445544554,
      "grad_norm": 0.4446244537830353,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.3717,
      "step": 124
    },
    {
      "epoch": 0.24752475247524752,
      "grad_norm": 0.46259209513664246,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 2.3752,
      "step": 125
    },
    {
      "epoch": 0.2495049504950495,
      "grad_norm": 0.46516507863998413,
      "learning_rate": 3.298534127791785e-05,
      "loss": 2.478,
      "step": 126
    },
    {
      "epoch": 0.2514851485148515,
      "grad_norm": 0.4979885518550873,
      "learning_rate": 3.221030765387417e-05,
      "loss": 2.4548,
      "step": 127
    },
    {
      "epoch": 0.25346534653465347,
      "grad_norm": 0.4794023931026459,
      "learning_rate": 3.144013755408895e-05,
      "loss": 2.4038,
      "step": 128
    },
    {
      "epoch": 0.25544554455445545,
      "grad_norm": 0.49073275923728943,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 2.4692,
      "step": 129
    },
    {
      "epoch": 0.25742574257425743,
      "grad_norm": 0.4890812039375305,
      "learning_rate": 2.991522876735154e-05,
      "loss": 2.4725,
      "step": 130
    },
    {
      "epoch": 0.2594059405940594,
      "grad_norm": 0.5170512795448303,
      "learning_rate": 2.916090697523549e-05,
      "loss": 2.4952,
      "step": 131
    },
    {
      "epoch": 0.2613861386138614,
      "grad_norm": 0.5190766453742981,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.4031,
      "step": 132
    },
    {
      "epoch": 0.2633663366336634,
      "grad_norm": 0.5270561575889587,
      "learning_rate": 2.766955965735968e-05,
      "loss": 2.3425,
      "step": 133
    },
    {
      "epoch": 0.26534653465346536,
      "grad_norm": 0.5538230538368225,
      "learning_rate": 2.693294185106562e-05,
      "loss": 2.3901,
      "step": 134
    },
    {
      "epoch": 0.26732673267326734,
      "grad_norm": 0.5554892420768738,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.4567,
      "step": 135
    },
    {
      "epoch": 0.2693069306930693,
      "grad_norm": 0.5523017644882202,
      "learning_rate": 2.547882480847461e-05,
      "loss": 2.5129,
      "step": 136
    },
    {
      "epoch": 0.2712871287128713,
      "grad_norm": 0.6482225656509399,
      "learning_rate": 2.476172311325783e-05,
      "loss": 2.4011,
      "step": 137
    },
    {
      "epoch": 0.2732673267326733,
      "grad_norm": 0.6002235412597656,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.3962,
      "step": 138
    },
    {
      "epoch": 0.27524752475247527,
      "grad_norm": 0.59397292137146,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 2.3549,
      "step": 139
    },
    {
      "epoch": 0.27722772277227725,
      "grad_norm": 0.6597419381141663,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.4218,
      "step": 140
    },
    {
      "epoch": 0.27920792079207923,
      "grad_norm": 0.6826123595237732,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.505,
      "step": 141
    },
    {
      "epoch": 0.2811881188118812,
      "grad_norm": 0.6769988536834717,
      "learning_rate": 2.128356686585282e-05,
      "loss": 2.5347,
      "step": 142
    },
    {
      "epoch": 0.28316831683168314,
      "grad_norm": 0.6855747699737549,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.4968,
      "step": 143
    },
    {
      "epoch": 0.2851485148514851,
      "grad_norm": 0.7421025037765503,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.4316,
      "step": 144
    },
    {
      "epoch": 0.2871287128712871,
      "grad_norm": 0.8343930840492249,
      "learning_rate": 1.928936436551661e-05,
      "loss": 2.628,
      "step": 145
    },
    {
      "epoch": 0.2891089108910891,
      "grad_norm": 0.8693667054176331,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 2.5544,
      "step": 146
    },
    {
      "epoch": 0.29108910891089107,
      "grad_norm": 0.8975053429603577,
      "learning_rate": 1.800157297483417e-05,
      "loss": 2.5397,
      "step": 147
    },
    {
      "epoch": 0.29306930693069305,
      "grad_norm": 1.0293112993240356,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 2.4897,
      "step": 148
    },
    {
      "epoch": 0.29504950495049503,
      "grad_norm": 1.0839552879333496,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 2.4368,
      "step": 149
    },
    {
      "epoch": 0.297029702970297,
      "grad_norm": 1.4868404865264893,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.5423,
      "step": 150
    },
    {
      "epoch": 0.297029702970297,
      "eval_loss": 2.4530744552612305,
      "eval_runtime": 17.5801,
      "eval_samples_per_second": 48.407,
      "eval_steps_per_second": 12.116,
      "step": 150
    },
    {
      "epoch": 0.299009900990099,
      "grad_norm": 0.27213677763938904,
      "learning_rate": 1.553232954407171e-05,
      "loss": 2.2897,
      "step": 151
    },
    {
      "epoch": 0.300990099009901,
      "grad_norm": 0.30643248558044434,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 2.2866,
      "step": 152
    },
    {
      "epoch": 0.30297029702970296,
      "grad_norm": 0.3153526484966278,
      "learning_rate": 1.435357758543015e-05,
      "loss": 2.2968,
      "step": 153
    },
    {
      "epoch": 0.30495049504950494,
      "grad_norm": 0.3769310414791107,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 2.3538,
      "step": 154
    },
    {
      "epoch": 0.3069306930693069,
      "grad_norm": 0.38436412811279297,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 2.4058,
      "step": 155
    },
    {
      "epoch": 0.3089108910891089,
      "grad_norm": 0.3720669448375702,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 2.3245,
      "step": 156
    },
    {
      "epoch": 0.3108910891089109,
      "grad_norm": 0.38330885767936707,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 2.3375,
      "step": 157
    },
    {
      "epoch": 0.31287128712871287,
      "grad_norm": 0.3681381046772003,
      "learning_rate": 1.157994445715706e-05,
      "loss": 2.333,
      "step": 158
    },
    {
      "epoch": 0.31485148514851485,
      "grad_norm": 0.3880598843097687,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 2.3011,
      "step": 159
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 0.4010571837425232,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 2.4319,
      "step": 160
    },
    {
      "epoch": 0.3188118811881188,
      "grad_norm": 0.38602215051651,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 2.3537,
      "step": 161
    },
    {
      "epoch": 0.3207920792079208,
      "grad_norm": 0.4502077102661133,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.3703,
      "step": 162
    },
    {
      "epoch": 0.3227722772277228,
      "grad_norm": 0.3963245451450348,
      "learning_rate": 9.068759265665384e-06,
      "loss": 2.3948,
      "step": 163
    },
    {
      "epoch": 0.32475247524752476,
      "grad_norm": 0.41620874404907227,
      "learning_rate": 8.599558442598998e-06,
      "loss": 2.3384,
      "step": 164
    },
    {
      "epoch": 0.32673267326732675,
      "grad_norm": 0.42003533244132996,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.4325,
      "step": 165
    },
    {
      "epoch": 0.3287128712871287,
      "grad_norm": 0.42814120650291443,
      "learning_rate": 7.695237378953223e-06,
      "loss": 2.4259,
      "step": 166
    },
    {
      "epoch": 0.3306930693069307,
      "grad_norm": 0.4195343852043152,
      "learning_rate": 7.260364370723044e-06,
      "loss": 2.505,
      "step": 167
    },
    {
      "epoch": 0.3326732673267327,
      "grad_norm": 0.4151943325996399,
      "learning_rate": 6.837175952121306e-06,
      "loss": 2.3287,
      "step": 168
    },
    {
      "epoch": 0.3346534653465347,
      "grad_norm": 0.40720734000205994,
      "learning_rate": 6.425787818636131e-06,
      "loss": 2.3853,
      "step": 169
    },
    {
      "epoch": 0.33663366336633666,
      "grad_norm": 0.4406540095806122,
      "learning_rate": 6.026312439675552e-06,
      "loss": 2.3312,
      "step": 170
    },
    {
      "epoch": 0.33861386138613864,
      "grad_norm": 0.40804576873779297,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 2.4675,
      "step": 171
    },
    {
      "epoch": 0.3405940594059406,
      "grad_norm": 0.45125508308410645,
      "learning_rate": 5.263533508961827e-06,
      "loss": 2.3798,
      "step": 172
    },
    {
      "epoch": 0.3425742574257426,
      "grad_norm": 0.4223173260688782,
      "learning_rate": 4.900438493352055e-06,
      "loss": 2.3363,
      "step": 173
    },
    {
      "epoch": 0.3445544554455445,
      "grad_norm": 0.4646742343902588,
      "learning_rate": 4.549673247541875e-06,
      "loss": 2.4895,
      "step": 174
    },
    {
      "epoch": 0.3465346534653465,
      "grad_norm": 0.4424516260623932,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 2.4563,
      "step": 175
    },
    {
      "epoch": 0.3485148514851485,
      "grad_norm": 0.4610097110271454,
      "learning_rate": 3.885512251130763e-06,
      "loss": 2.4076,
      "step": 176
    },
    {
      "epoch": 0.3504950495049505,
      "grad_norm": 0.45616912841796875,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 2.3875,
      "step": 177
    },
    {
      "epoch": 0.35247524752475246,
      "grad_norm": 0.47183099389076233,
      "learning_rate": 3.271776770026963e-06,
      "loss": 2.4123,
      "step": 178
    },
    {
      "epoch": 0.35445544554455444,
      "grad_norm": 0.4817582964897156,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 2.4892,
      "step": 179
    },
    {
      "epoch": 0.3564356435643564,
      "grad_norm": 0.4945870041847229,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.4538,
      "step": 180
    },
    {
      "epoch": 0.3584158415841584,
      "grad_norm": 0.4918562173843384,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.4335,
      "step": 181
    },
    {
      "epoch": 0.3603960396039604,
      "grad_norm": 0.5189668536186218,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 2.4304,
      "step": 182
    },
    {
      "epoch": 0.36237623762376237,
      "grad_norm": 0.4953053295612335,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.3854,
      "step": 183
    },
    {
      "epoch": 0.36435643564356435,
      "grad_norm": 0.5314679145812988,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 2.4221,
      "step": 184
    },
    {
      "epoch": 0.36633663366336633,
      "grad_norm": 0.5215020775794983,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.4673,
      "step": 185
    },
    {
      "epoch": 0.3683168316831683,
      "grad_norm": 0.5795071125030518,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.4772,
      "step": 186
    },
    {
      "epoch": 0.3702970297029703,
      "grad_norm": 0.5816572308540344,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 2.4215,
      "step": 187
    },
    {
      "epoch": 0.3722772277227723,
      "grad_norm": 0.5883288979530334,
      "learning_rate": 9.810017062595322e-07,
      "loss": 2.4998,
      "step": 188
    },
    {
      "epoch": 0.37425742574257426,
      "grad_norm": 0.6194007992744446,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.463,
      "step": 189
    },
    {
      "epoch": 0.37623762376237624,
      "grad_norm": 0.6459846496582031,
      "learning_rate": 6.819348298638839e-07,
      "loss": 2.4646,
      "step": 190
    },
    {
      "epoch": 0.3782178217821782,
      "grad_norm": 0.6372405290603638,
      "learning_rate": 5.526064699265753e-07,
      "loss": 2.4556,
      "step": 191
    },
    {
      "epoch": 0.3801980198019802,
      "grad_norm": 0.7288736701011658,
      "learning_rate": 4.367965336512403e-07,
      "loss": 2.6296,
      "step": 192
    },
    {
      "epoch": 0.3821782178217822,
      "grad_norm": 0.7070505023002625,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 2.4594,
      "step": 193
    },
    {
      "epoch": 0.38415841584158417,
      "grad_norm": 0.7311199903488159,
      "learning_rate": 2.458548727494292e-07,
      "loss": 2.5628,
      "step": 194
    },
    {
      "epoch": 0.38613861386138615,
      "grad_norm": 0.7641336917877197,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 2.4101,
      "step": 195
    },
    {
      "epoch": 0.38811881188118813,
      "grad_norm": 0.8075855374336243,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 2.4606,
      "step": 196
    },
    {
      "epoch": 0.3900990099009901,
      "grad_norm": 0.924250066280365,
      "learning_rate": 6.150154258476315e-08,
      "loss": 2.5814,
      "step": 197
    },
    {
      "epoch": 0.3920792079207921,
      "grad_norm": 0.9708317518234253,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 2.5901,
      "step": 198
    },
    {
      "epoch": 0.3940594059405941,
      "grad_norm": 1.2108420133590698,
      "learning_rate": 6.834750376549792e-09,
      "loss": 2.5522,
      "step": 199
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 1.611008882522583,
      "learning_rate": 0.0,
      "loss": 2.6577,
      "step": 200
    },
    {
      "epoch": 0.39603960396039606,
      "eval_loss": 2.4489593505859375,
      "eval_runtime": 17.5081,
      "eval_samples_per_second": 48.606,
      "eval_steps_per_second": 12.166,
      "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": 4.340955879781171e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}