{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.033772374197906116,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033772374197906115,
      "grad_norm": 6.999200559221208e-05,
      "learning_rate": 5e-06,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.00033772374197906115,
      "eval_loss": 11.5,
      "eval_runtime": 38.0491,
      "eval_samples_per_second": 131.067,
      "eval_steps_per_second": 65.547,
      "step": 1
    },
    {
      "epoch": 0.0006754474839581223,
      "grad_norm": 5.612642053165473e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0010131712259371835,
      "grad_norm": 0.00011171244841534644,
      "learning_rate": 1.5e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0013508949679162446,
      "grad_norm": 6.527295772684738e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0016886187098953055,
      "grad_norm": 0.00010032207501353696,
      "learning_rate": 2.5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.002026342451874367,
      "grad_norm": 6.297726213233545e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.002364066193853428,
      "grad_norm": 0.00010159278463106602,
      "learning_rate": 3.5e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.002701789935832489,
      "grad_norm": 6.908881186973304e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.00303951367781155,
      "grad_norm": 0.00010548412683419883,
      "learning_rate": 4.5e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.003377237419790611,
      "grad_norm": 0.00010045844101114199,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.0037149611617696724,
      "grad_norm": 0.00010918975749518722,
      "learning_rate": 5.500000000000001e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.004052684903748734,
      "grad_norm": 0.00010634872887749225,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.004390408645727794,
      "grad_norm": 6.084080450818874e-05,
      "learning_rate": 6.500000000000001e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.004728132387706856,
      "grad_norm": 8.961093408288434e-05,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.005065856129685917,
      "grad_norm": 7.892983558122069e-05,
      "learning_rate": 7.500000000000001e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.005403579871664978,
      "grad_norm": 7.510028081014752e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.005741303613644039,
      "grad_norm": 0.00010316520638298243,
      "learning_rate": 8.5e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.0060790273556231,
      "grad_norm": 0.00015889042697381228,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.006416751097602162,
      "grad_norm": 9.389503247803077e-05,
      "learning_rate": 9.5e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.006754474839581222,
      "grad_norm": 0.00012303520634304732,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.0070921985815602835,
      "grad_norm": 0.00016235452494584024,
      "learning_rate": 9.999238475781957e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.007429922323539345,
      "grad_norm": 0.00012188320397399366,
      "learning_rate": 9.99695413509548e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.007767646065518406,
      "grad_norm": 0.00015171366976574063,
      "learning_rate": 9.99314767377287e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.008105369807497468,
      "grad_norm": 9.316073555964977e-05,
      "learning_rate": 9.987820251299122e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.008443093549476529,
      "grad_norm": 0.00014290536637417972,
      "learning_rate": 9.980973490458728e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.008780817291455589,
      "grad_norm": 0.00015599915059283376,
      "learning_rate": 9.972609476841367e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.00911854103343465,
      "grad_norm": 0.00015680905198678374,
      "learning_rate": 9.962730758206611e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.009456264775413711,
      "grad_norm": 0.00016664821305312216,
      "learning_rate": 9.951340343707852e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.009793988517392773,
      "grad_norm": 0.0001463688095100224,
      "learning_rate": 9.938441702975689e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.010131712259371834,
      "grad_norm": 0.0001783478946890682,
      "learning_rate": 9.924038765061042e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.010469436001350895,
      "grad_norm": 0.0001655457599554211,
      "learning_rate": 9.908135917238321e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.010807159743329957,
      "grad_norm": 0.00018240793724544346,
      "learning_rate": 9.890738003669029e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.011144883485309016,
      "grad_norm": 0.00016705192683730274,
      "learning_rate": 9.871850323926177e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.011482607227288078,
      "grad_norm": 0.0002768947451841086,
      "learning_rate": 9.851478631379982e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.01182033096926714,
      "grad_norm": 0.00024317330098710954,
      "learning_rate": 9.829629131445342e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.0121580547112462,
      "grad_norm": 0.00013411836698651314,
      "learning_rate": 9.806308479691595e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.012495778453225262,
      "grad_norm": 0.00028809363720938563,
      "learning_rate": 9.781523779815179e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.012833502195204323,
      "grad_norm": 0.00029307673685252666,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.013171225937183385,
      "grad_norm": 0.0002233909472124651,
      "learning_rate": 9.727592877996585e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.013508949679162444,
      "grad_norm": 0.0002125003666151315,
      "learning_rate": 9.698463103929542e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.013846673421141506,
      "grad_norm": 0.00015506868658121675,
      "learning_rate": 9.667902132486009e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.014184397163120567,
      "grad_norm": 0.00023671003873459995,
      "learning_rate": 9.635919272833938e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.014522120905099628,
      "grad_norm": 0.00023820622300263494,
      "learning_rate": 9.602524267262203e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.01485984464707869,
      "grad_norm": 0.00013906476669944823,
      "learning_rate": 9.567727288213005e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.015197568389057751,
      "grad_norm": 0.00024479327839799225,
      "learning_rate": 9.53153893518325e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.015535292131036813,
      "grad_norm": 0.0002795088803395629,
      "learning_rate": 9.493970231495835e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 0.00026209637871943414,
      "learning_rate": 9.45503262094184e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.016210739614994935,
      "grad_norm": 0.00022261285630520433,
      "learning_rate": 9.414737964294636e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.016548463356973995,
      "grad_norm": 0.0002231644029961899,
      "learning_rate": 9.373098535696979e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.016886187098953058,
      "grad_norm": 0.00023359505576081574,
      "learning_rate": 9.330127018922194e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.016886187098953058,
      "eval_loss": 11.5,
      "eval_runtime": 38.1051,
      "eval_samples_per_second": 130.875,
      "eval_steps_per_second": 65.451,
      "step": 50
    },
    {
      "epoch": 0.017223910840932118,
      "grad_norm": 0.0004388255765661597,
      "learning_rate": 9.285836503510562e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.017561634582911177,
      "grad_norm": 0.00034231445170007646,
      "learning_rate": 9.24024048078213e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.01789935832489024,
      "grad_norm": 0.00040279701352119446,
      "learning_rate": 9.193352839727121e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.0182370820668693,
      "grad_norm": 0.00048692570999264717,
      "learning_rate": 9.145187862775209e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.018574805808848363,
      "grad_norm": 0.0004796187567990273,
      "learning_rate": 9.09576022144496e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.018912529550827423,
      "grad_norm": 0.0004256981483194977,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.019250253292806486,
      "grad_norm": 0.0003702337562572211,
      "learning_rate": 8.993177550236464e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.019587977034785545,
      "grad_norm": 0.00028856948483735323,
      "learning_rate": 8.940053768033609e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.019925700776764605,
      "grad_norm": 0.00043020248995162547,
      "learning_rate": 8.885729807284856e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.020263424518743668,
      "grad_norm": 0.00032656811526976526,
      "learning_rate": 8.83022221559489e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.020601148260722728,
      "grad_norm": 0.00044006985262967646,
      "learning_rate": 8.773547901113862e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.02093887200270179,
      "grad_norm": 0.0005264987121336162,
      "learning_rate": 8.715724127386972e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 0.0005930354818701744,
      "learning_rate": 8.656768508095853e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.021614319486659914,
      "grad_norm": 0.0004631902265828103,
      "learning_rate": 8.596699001693255e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.021952043228638973,
      "grad_norm": 0.0004996751667931676,
      "learning_rate": 8.535533905932738e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.022289766970618033,
      "grad_norm": 0.0005587644409388304,
      "learning_rate": 8.473291852294987e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.022627490712597096,
      "grad_norm": 0.0005852883914485574,
      "learning_rate": 8.409991800312493e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.022965214454576156,
      "grad_norm": 0.0007204718422144651,
      "learning_rate": 8.345653031794292e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.02330293819655522,
      "grad_norm": 0.0005952971987426281,
      "learning_rate": 8.280295144952536e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.02364066193853428,
      "grad_norm": 0.0005659193848259747,
      "learning_rate": 8.213938048432697e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.02397838568051334,
      "grad_norm": 0.0004821221227757633,
      "learning_rate": 8.146601955249188e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.0243161094224924,
      "grad_norm": 0.00043129047844558954,
      "learning_rate": 8.07830737662829e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.02465383316447146,
      "grad_norm": 0.0007432058919221163,
      "learning_rate": 8.009075115760243e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.024991556906450524,
      "grad_norm": 0.0005778361228294671,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.025329280648429583,
      "grad_norm": 0.0006119939498603344,
      "learning_rate": 7.86788218175523e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.025667004390408647,
      "grad_norm": 0.0006990509573370218,
      "learning_rate": 7.795964517353735e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.026004728132387706,
      "grad_norm": 0.000691780005581677,
      "learning_rate": 7.723195175075136e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.02634245187436677,
      "grad_norm": 0.0007424818468280137,
      "learning_rate": 7.649596321166024e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.02668017561634583,
      "grad_norm": 0.0009253322496078908,
      "learning_rate": 7.575190374550272e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.02701789935832489,
      "grad_norm": 0.0006558927707374096,
      "learning_rate": 7.500000000000001e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.02735562310030395,
      "grad_norm": 0.000801301037427038,
      "learning_rate": 7.424048101231686e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.02769334684228301,
      "grad_norm": 0.0007340286974795163,
      "learning_rate": 7.347357813929454e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.028031070584262074,
      "grad_norm": 0.0005543944425880909,
      "learning_rate": 7.269952498697734e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 0.0004185195139143616,
      "learning_rate": 7.191855733945387e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.028706518068220197,
      "grad_norm": 0.0008723873761482537,
      "learning_rate": 7.113091308703498e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.029044241810199257,
      "grad_norm": 0.0006252967286854982,
      "learning_rate": 7.033683215379002e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.029381965552178316,
      "grad_norm": 0.0008132215589284897,
      "learning_rate": 6.953655642446368e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.02971968929415738,
      "grad_norm": 0.0006520528695546091,
      "learning_rate": 6.873032967079561e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.03005741303613644,
      "grad_norm": 0.0006046611815690994,
      "learning_rate": 6.7918397477265e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.030395136778115502,
      "grad_norm": 0.0007351114763878286,
      "learning_rate": 6.710100716628344e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.030732860520094562,
      "grad_norm": 0.0005443833651952446,
      "learning_rate": 6.627840772285784e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.031070584262073625,
      "grad_norm": 0.0007517460617236793,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.031408308004052685,
      "grad_norm": 0.0006298055523075163,
      "learning_rate": 6.461858523613684e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 0.0006449134671129286,
      "learning_rate": 6.378186779084995e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.032083755488010804,
      "grad_norm": 0.0005613227258436382,
      "learning_rate": 6.294095225512603e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.03242147922998987,
      "grad_norm": 0.0006533685373142362,
      "learning_rate": 6.209609477998338e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.03275920297196893,
      "grad_norm": 0.000610053539276123,
      "learning_rate": 6.124755271719325e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.03309692671394799,
      "grad_norm": 0.0006236035260371864,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.03343465045592705,
      "grad_norm": 0.0006816457607783377,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.033772374197906116,
      "grad_norm": 0.0008262648480013013,
      "learning_rate": 5.868240888334653e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.033772374197906116,
      "eval_loss": 11.5,
      "eval_runtime": 38.395,
      "eval_samples_per_second": 129.887,
      "eval_steps_per_second": 64.956,
      "step": 100
    }
  ],
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 22872706646016.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}