{
  "best_metric": 0.8298870921134949,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.3780718336483932,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003780718336483932,
      "grad_norm": 17.58527374267578,
      "learning_rate": 1e-05,
      "loss": 4.6715,
      "step": 1
    },
    {
      "epoch": 0.003780718336483932,
      "eval_loss": 1.5147686004638672,
      "eval_runtime": 32.2384,
      "eval_samples_per_second": 13.834,
      "eval_steps_per_second": 3.474,
      "step": 1
    },
    {
      "epoch": 0.007561436672967864,
      "grad_norm": 18.938438415527344,
      "learning_rate": 2e-05,
      "loss": 4.6865,
      "step": 2
    },
    {
      "epoch": 0.011342155009451797,
      "grad_norm": 19.244638442993164,
      "learning_rate": 3e-05,
      "loss": 4.5627,
      "step": 3
    },
    {
      "epoch": 0.015122873345935728,
      "grad_norm": 18.532451629638672,
      "learning_rate": 4e-05,
      "loss": 4.3446,
      "step": 4
    },
    {
      "epoch": 0.01890359168241966,
      "grad_norm": 13.675602912902832,
      "learning_rate": 5e-05,
      "loss": 4.0127,
      "step": 5
    },
    {
      "epoch": 0.022684310018903593,
      "grad_norm": 13.681532859802246,
      "learning_rate": 6e-05,
      "loss": 4.3083,
      "step": 6
    },
    {
      "epoch": 0.026465028355387523,
      "grad_norm": 13.697336196899414,
      "learning_rate": 7e-05,
      "loss": 4.0012,
      "step": 7
    },
    {
      "epoch": 0.030245746691871456,
      "grad_norm": 11.588497161865234,
      "learning_rate": 8e-05,
      "loss": 4.1113,
      "step": 8
    },
    {
      "epoch": 0.034026465028355386,
      "grad_norm": 10.041873931884766,
      "learning_rate": 9e-05,
      "loss": 3.9785,
      "step": 9
    },
    {
      "epoch": 0.03780718336483932,
      "grad_norm": 10.903011322021484,
      "learning_rate": 0.0001,
      "loss": 4.0143,
      "step": 10
    },
    {
      "epoch": 0.04158790170132325,
      "grad_norm": 9.505345344543457,
      "learning_rate": 9.99695413509548e-05,
      "loss": 4.2929,
      "step": 11
    },
    {
      "epoch": 0.045368620037807186,
      "grad_norm": 9.531927108764648,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.9884,
      "step": 12
    },
    {
      "epoch": 0.04914933837429111,
      "grad_norm": 8.5378999710083,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.8258,
      "step": 13
    },
    {
      "epoch": 0.052930056710775046,
      "grad_norm": 9.409659385681152,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.582,
      "step": 14
    },
    {
      "epoch": 0.05671077504725898,
      "grad_norm": 10.614547729492188,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.5068,
      "step": 15
    },
    {
      "epoch": 0.06049149338374291,
      "grad_norm": 10.875083923339844,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.7393,
      "step": 16
    },
    {
      "epoch": 0.06427221172022685,
      "grad_norm": 9.732378959655762,
      "learning_rate": 9.851478631379982e-05,
      "loss": 3.722,
      "step": 17
    },
    {
      "epoch": 0.06805293005671077,
      "grad_norm": 11.916670799255371,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.791,
      "step": 18
    },
    {
      "epoch": 0.07183364839319471,
      "grad_norm": 12.634649276733398,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.9867,
      "step": 19
    },
    {
      "epoch": 0.07561436672967864,
      "grad_norm": 8.961518287658691,
      "learning_rate": 9.698463103929542e-05,
      "loss": 3.4147,
      "step": 20
    },
    {
      "epoch": 0.07939508506616257,
      "grad_norm": 8.40068531036377,
      "learning_rate": 9.635919272833938e-05,
      "loss": 3.1031,
      "step": 21
    },
    {
      "epoch": 0.0831758034026465,
      "grad_norm": 9.77192497253418,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.6041,
      "step": 22
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 9.314102172851562,
      "learning_rate": 9.493970231495835e-05,
      "loss": 3.7216,
      "step": 23
    },
    {
      "epoch": 0.09073724007561437,
      "grad_norm": 10.22673511505127,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.1015,
      "step": 24
    },
    {
      "epoch": 0.0945179584120983,
      "grad_norm": 9.64807415008545,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.341,
      "step": 25
    },
    {
      "epoch": 0.09829867674858223,
      "grad_norm": 8.940032005310059,
      "learning_rate": 9.24024048078213e-05,
      "loss": 3.2157,
      "step": 26
    },
    {
      "epoch": 0.10207939508506617,
      "grad_norm": 10.569997787475586,
      "learning_rate": 9.145187862775209e-05,
      "loss": 3.5153,
      "step": 27
    },
    {
      "epoch": 0.10586011342155009,
      "grad_norm": 8.026988983154297,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.1949,
      "step": 28
    },
    {
      "epoch": 0.10964083175803403,
      "grad_norm": 8.490434646606445,
      "learning_rate": 8.940053768033609e-05,
      "loss": 3.5454,
      "step": 29
    },
    {
      "epoch": 0.11342155009451796,
      "grad_norm": 9.074066162109375,
      "learning_rate": 8.83022221559489e-05,
      "loss": 3.3876,
      "step": 30
    },
    {
      "epoch": 0.11720226843100189,
      "grad_norm": 10.126070022583008,
      "learning_rate": 8.715724127386972e-05,
      "loss": 3.5297,
      "step": 31
    },
    {
      "epoch": 0.12098298676748583,
      "grad_norm": 9.458115577697754,
      "learning_rate": 8.596699001693255e-05,
      "loss": 3.3732,
      "step": 32
    },
    {
      "epoch": 0.12476370510396975,
      "grad_norm": 8.374913215637207,
      "learning_rate": 8.473291852294987e-05,
      "loss": 3.2017,
      "step": 33
    },
    {
      "epoch": 0.1285444234404537,
      "grad_norm": 9.311302185058594,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.4341,
      "step": 34
    },
    {
      "epoch": 0.1323251417769376,
      "grad_norm": 8.4367036819458,
      "learning_rate": 8.213938048432697e-05,
      "loss": 3.263,
      "step": 35
    },
    {
      "epoch": 0.13610586011342155,
      "grad_norm": 8.591708183288574,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.214,
      "step": 36
    },
    {
      "epoch": 0.13988657844990549,
      "grad_norm": 10.549474716186523,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.8853,
      "step": 37
    },
    {
      "epoch": 0.14366729678638943,
      "grad_norm": 8.822783470153809,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.1999,
      "step": 38
    },
    {
      "epoch": 0.14744801512287334,
      "grad_norm": 9.879439353942871,
      "learning_rate": 7.649596321166024e-05,
      "loss": 3.7023,
      "step": 39
    },
    {
      "epoch": 0.15122873345935728,
      "grad_norm": 10.684730529785156,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.2861,
      "step": 40
    },
    {
      "epoch": 0.15500945179584122,
      "grad_norm": 8.875012397766113,
      "learning_rate": 7.347357813929454e-05,
      "loss": 3.4362,
      "step": 41
    },
    {
      "epoch": 0.15879017013232513,
      "grad_norm": 9.062248229980469,
      "learning_rate": 7.191855733945387e-05,
      "loss": 3.2334,
      "step": 42
    },
    {
      "epoch": 0.16257088846880907,
      "grad_norm": 8.561145782470703,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.8832,
      "step": 43
    },
    {
      "epoch": 0.166351606805293,
      "grad_norm": 10.574623107910156,
      "learning_rate": 6.873032967079561e-05,
      "loss": 3.5312,
      "step": 44
    },
    {
      "epoch": 0.17013232514177692,
      "grad_norm": 10.00291919708252,
      "learning_rate": 6.710100716628344e-05,
      "loss": 3.3973,
      "step": 45
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 8.725358963012695,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.964,
      "step": 46
    },
    {
      "epoch": 0.1776937618147448,
      "grad_norm": 11.551474571228027,
      "learning_rate": 6.378186779084995e-05,
      "loss": 3.247,
      "step": 47
    },
    {
      "epoch": 0.18147448015122875,
      "grad_norm": 12.168755531311035,
      "learning_rate": 6.209609477998338e-05,
      "loss": 3.7066,
      "step": 48
    },
    {
      "epoch": 0.18525519848771266,
      "grad_norm": 14.238049507141113,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 3.1095,
      "step": 49
    },
    {
      "epoch": 0.1890359168241966,
      "grad_norm": 10.556962966918945,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.9489,
      "step": 50
    },
    {
      "epoch": 0.1890359168241966,
      "eval_loss": 0.8817651867866516,
      "eval_runtime": 32.7884,
      "eval_samples_per_second": 13.602,
      "eval_steps_per_second": 3.416,
      "step": 50
    },
    {
      "epoch": 0.19281663516068054,
      "grad_norm": 8.632866859436035,
      "learning_rate": 5.695865504800327e-05,
      "loss": 3.5474,
      "step": 51
    },
    {
      "epoch": 0.19659735349716445,
      "grad_norm": 8.222471237182617,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.5246,
      "step": 52
    },
    {
      "epoch": 0.2003780718336484,
      "grad_norm": 7.276666164398193,
      "learning_rate": 5.348782368720626e-05,
      "loss": 3.698,
      "step": 53
    },
    {
      "epoch": 0.20415879017013233,
      "grad_norm": 7.079733371734619,
      "learning_rate": 5.174497483512506e-05,
      "loss": 3.4229,
      "step": 54
    },
    {
      "epoch": 0.20793950850661624,
      "grad_norm": 7.484187602996826,
      "learning_rate": 5e-05,
      "loss": 3.6525,
      "step": 55
    },
    {
      "epoch": 0.21172022684310018,
      "grad_norm": 7.31273889541626,
      "learning_rate": 4.825502516487497e-05,
      "loss": 3.2383,
      "step": 56
    },
    {
      "epoch": 0.21550094517958412,
      "grad_norm": 7.360807418823242,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 3.3803,
      "step": 57
    },
    {
      "epoch": 0.21928166351606806,
      "grad_norm": 6.599316596984863,
      "learning_rate": 4.477357683661734e-05,
      "loss": 3.2836,
      "step": 58
    },
    {
      "epoch": 0.22306238185255198,
      "grad_norm": 6.654892921447754,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 3.0898,
      "step": 59
    },
    {
      "epoch": 0.22684310018903592,
      "grad_norm": 8.16332721710205,
      "learning_rate": 4.131759111665349e-05,
      "loss": 3.5083,
      "step": 60
    },
    {
      "epoch": 0.23062381852551986,
      "grad_norm": 6.758691787719727,
      "learning_rate": 3.960441545911204e-05,
      "loss": 3.3828,
      "step": 61
    },
    {
      "epoch": 0.23440453686200377,
      "grad_norm": 7.5050249099731445,
      "learning_rate": 3.790390522001662e-05,
      "loss": 3.6234,
      "step": 62
    },
    {
      "epoch": 0.2381852551984877,
      "grad_norm": 6.148810863494873,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.9958,
      "step": 63
    },
    {
      "epoch": 0.24196597353497165,
      "grad_norm": 7.6679558753967285,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.6935,
      "step": 64
    },
    {
      "epoch": 0.24574669187145556,
      "grad_norm": 7.433490753173828,
      "learning_rate": 3.289899283371657e-05,
      "loss": 3.2861,
      "step": 65
    },
    {
      "epoch": 0.2495274102079395,
      "grad_norm": 8.658961296081543,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.3368,
      "step": 66
    },
    {
      "epoch": 0.2533081285444234,
      "grad_norm": 7.807982444763184,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 3.2657,
      "step": 67
    },
    {
      "epoch": 0.2570888468809074,
      "grad_norm": 8.201922416687012,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 3.2938,
      "step": 68
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 7.491893768310547,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 3.3305,
      "step": 69
    },
    {
      "epoch": 0.2646502835538752,
      "grad_norm": 7.460444450378418,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.4191,
      "step": 70
    },
    {
      "epoch": 0.2684310018903592,
      "grad_norm": 7.707852363586426,
      "learning_rate": 2.350403678833976e-05,
      "loss": 3.5759,
      "step": 71
    },
    {
      "epoch": 0.2722117202268431,
      "grad_norm": 8.57703971862793,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 3.1639,
      "step": 72
    },
    {
      "epoch": 0.27599243856332706,
      "grad_norm": 7.847999572753906,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.3657,
      "step": 73
    },
    {
      "epoch": 0.27977315689981097,
      "grad_norm": 7.267697811126709,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 3.3797,
      "step": 74
    },
    {
      "epoch": 0.2835538752362949,
      "grad_norm": 9.05839729309082,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 3.5028,
      "step": 75
    },
    {
      "epoch": 0.28733459357277885,
      "grad_norm": 7.292295455932617,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 3.3584,
      "step": 76
    },
    {
      "epoch": 0.29111531190926276,
      "grad_norm": 8.454133033752441,
      "learning_rate": 1.526708147705013e-05,
      "loss": 3.2899,
      "step": 77
    },
    {
      "epoch": 0.2948960302457467,
      "grad_norm": 8.45421314239502,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 3.3678,
      "step": 78
    },
    {
      "epoch": 0.29867674858223064,
      "grad_norm": 7.015564441680908,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 3.2794,
      "step": 79
    },
    {
      "epoch": 0.30245746691871456,
      "grad_norm": 7.422765254974365,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 3.3825,
      "step": 80
    },
    {
      "epoch": 0.30623818525519847,
      "grad_norm": 6.922229290008545,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 3.2878,
      "step": 81
    },
    {
      "epoch": 0.31001890359168244,
      "grad_norm": 7.0517578125,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.0816,
      "step": 82
    },
    {
      "epoch": 0.31379962192816635,
      "grad_norm": 7.885040283203125,
      "learning_rate": 8.548121372247918e-06,
      "loss": 3.0925,
      "step": 83
    },
    {
      "epoch": 0.31758034026465026,
      "grad_norm": 7.8887224197387695,
      "learning_rate": 7.597595192178702e-06,
      "loss": 3.5063,
      "step": 84
    },
    {
      "epoch": 0.32136105860113423,
      "grad_norm": 7.691339492797852,
      "learning_rate": 6.698729810778065e-06,
      "loss": 3.3699,
      "step": 85
    },
    {
      "epoch": 0.32514177693761814,
      "grad_norm": 7.647983551025391,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.9867,
      "step": 86
    },
    {
      "epoch": 0.32892249527410206,
      "grad_norm": 8.371914863586426,
      "learning_rate": 5.060297685041659e-06,
      "loss": 3.2845,
      "step": 87
    },
    {
      "epoch": 0.332703213610586,
      "grad_norm": 9.8147611618042,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.6608,
      "step": 88
    },
    {
      "epoch": 0.33648393194706994,
      "grad_norm": 8.83012866973877,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 3.3593,
      "step": 89
    },
    {
      "epoch": 0.34026465028355385,
      "grad_norm": 8.104722023010254,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 3.2901,
      "step": 90
    },
    {
      "epoch": 0.3440453686200378,
      "grad_norm": 9.367162704467773,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 3.5657,
      "step": 91
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 8.073724746704102,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.3694,
      "step": 92
    },
    {
      "epoch": 0.3516068052930057,
      "grad_norm": 8.500439643859863,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 3.5953,
      "step": 93
    },
    {
      "epoch": 0.3553875236294896,
      "grad_norm": 8.613424301147461,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 3.6281,
      "step": 94
    },
    {
      "epoch": 0.3591682419659735,
      "grad_norm": 9.02153491973877,
      "learning_rate": 7.596123493895991e-07,
      "loss": 3.157,
      "step": 95
    },
    {
      "epoch": 0.3629489603024575,
      "grad_norm": 8.697141647338867,
      "learning_rate": 4.865965629214819e-07,
      "loss": 3.2948,
      "step": 96
    },
    {
      "epoch": 0.3667296786389414,
      "grad_norm": 9.122673034667969,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 3.3452,
      "step": 97
    },
    {
      "epoch": 0.3705103969754253,
      "grad_norm": 9.09151840209961,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 3.197,
      "step": 98
    },
    {
      "epoch": 0.3742911153119093,
      "grad_norm": 10.097582817077637,
      "learning_rate": 3.04586490452119e-08,
      "loss": 3.0201,
      "step": 99
    },
    {
      "epoch": 0.3780718336483932,
      "grad_norm": 15.321501731872559,
      "learning_rate": 0.0,
      "loss": 3.4797,
      "step": 100
    },
    {
      "epoch": 0.3780718336483932,
      "eval_loss": 0.8298870921134949,
      "eval_runtime": 32.8857,
      "eval_samples_per_second": 13.562,
      "eval_steps_per_second": 3.406,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 1.414506945183744e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}