{
  "best_metric": 1.9593321084976196,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.017115960633290545,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017115960633290543,
      "grad_norm": 0.3355412781238556,
      "learning_rate": 5e-06,
      "loss": 2.1057,
      "step": 1
    },
    {
      "epoch": 0.00017115960633290543,
      "eval_loss": 2.140085220336914,
      "eval_runtime": 258.9714,
      "eval_samples_per_second": 37.996,
      "eval_steps_per_second": 18.998,
      "step": 1
    },
    {
      "epoch": 0.00034231921266581085,
      "grad_norm": 0.29723942279815674,
      "learning_rate": 1e-05,
      "loss": 2.0679,
      "step": 2
    },
    {
      "epoch": 0.0005134788189987163,
      "grad_norm": 0.31555816531181335,
      "learning_rate": 1.5e-05,
      "loss": 2.2761,
      "step": 3
    },
    {
      "epoch": 0.0006846384253316217,
      "grad_norm": 0.25562918186187744,
      "learning_rate": 2e-05,
      "loss": 1.881,
      "step": 4
    },
    {
      "epoch": 0.0008557980316645272,
      "grad_norm": 0.2628590166568756,
      "learning_rate": 2.5e-05,
      "loss": 2.0202,
      "step": 5
    },
    {
      "epoch": 0.0010269576379974327,
      "grad_norm": 0.25577813386917114,
      "learning_rate": 3e-05,
      "loss": 1.8699,
      "step": 6
    },
    {
      "epoch": 0.0011981172443303381,
      "grad_norm": 0.2143595963716507,
      "learning_rate": 3.5e-05,
      "loss": 1.7798,
      "step": 7
    },
    {
      "epoch": 0.0013692768506632434,
      "grad_norm": 0.24432000517845154,
      "learning_rate": 4e-05,
      "loss": 2.0537,
      "step": 8
    },
    {
      "epoch": 0.0015404364569961489,
      "grad_norm": 0.2208261489868164,
      "learning_rate": 4.5e-05,
      "loss": 1.7771,
      "step": 9
    },
    {
      "epoch": 0.0017115960633290544,
      "grad_norm": 0.22592778503894806,
      "learning_rate": 5e-05,
      "loss": 1.9607,
      "step": 10
    },
    {
      "epoch": 0.0018827556696619598,
      "grad_norm": 0.22352802753448486,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.0779,
      "step": 11
    },
    {
      "epoch": 0.0020539152759948653,
      "grad_norm": 0.22015997767448425,
      "learning_rate": 6e-05,
      "loss": 2.0472,
      "step": 12
    },
    {
      "epoch": 0.002225074882327771,
      "grad_norm": 0.20282255113124847,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.0319,
      "step": 13
    },
    {
      "epoch": 0.0023962344886606763,
      "grad_norm": 0.18487398326396942,
      "learning_rate": 7e-05,
      "loss": 2.1545,
      "step": 14
    },
    {
      "epoch": 0.0025673940949935813,
      "grad_norm": 0.15891127288341522,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0743,
      "step": 15
    },
    {
      "epoch": 0.002738553701326487,
      "grad_norm": 0.15739785134792328,
      "learning_rate": 8e-05,
      "loss": 1.9694,
      "step": 16
    },
    {
      "epoch": 0.0029097133076593923,
      "grad_norm": 0.1441313922405243,
      "learning_rate": 8.5e-05,
      "loss": 1.874,
      "step": 17
    },
    {
      "epoch": 0.0030808729139922978,
      "grad_norm": 0.1597474068403244,
      "learning_rate": 9e-05,
      "loss": 2.0868,
      "step": 18
    },
    {
      "epoch": 0.0032520325203252032,
      "grad_norm": 0.16448548436164856,
      "learning_rate": 9.5e-05,
      "loss": 2.0087,
      "step": 19
    },
    {
      "epoch": 0.0034231921266581087,
      "grad_norm": 0.15660351514816284,
      "learning_rate": 0.0001,
      "loss": 2.0582,
      "step": 20
    },
    {
      "epoch": 0.003594351732991014,
      "grad_norm": 0.1746840476989746,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.9058,
      "step": 21
    },
    {
      "epoch": 0.0037655113393239197,
      "grad_norm": 0.17854997515678406,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.9869,
      "step": 22
    },
    {
      "epoch": 0.003936670945656825,
      "grad_norm": 0.18090517818927765,
      "learning_rate": 9.99314767377287e-05,
      "loss": 2.0419,
      "step": 23
    },
    {
      "epoch": 0.004107830551989731,
      "grad_norm": 0.15388450026512146,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.0196,
      "step": 24
    },
    {
      "epoch": 0.004278990158322636,
      "grad_norm": 0.15999741852283478,
      "learning_rate": 9.980973490458728e-05,
      "loss": 2.0682,
      "step": 25
    },
    {
      "epoch": 0.004450149764655542,
      "grad_norm": 0.13543976843357086,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.9447,
      "step": 26
    },
    {
      "epoch": 0.004621309370988447,
      "grad_norm": 0.14296641945838928,
      "learning_rate": 9.962730758206611e-05,
      "loss": 2.1334,
      "step": 27
    },
    {
      "epoch": 0.004792468977321353,
      "grad_norm": 0.13348829746246338,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.9633,
      "step": 28
    },
    {
      "epoch": 0.004963628583654257,
      "grad_norm": 0.13364166021347046,
      "learning_rate": 9.938441702975689e-05,
      "loss": 2.0228,
      "step": 29
    },
    {
      "epoch": 0.005134788189987163,
      "grad_norm": 0.1257980912923813,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.8989,
      "step": 30
    },
    {
      "epoch": 0.005305947796320068,
      "grad_norm": 0.13509519398212433,
      "learning_rate": 9.908135917238321e-05,
      "loss": 1.952,
      "step": 31
    },
    {
      "epoch": 0.005477107402652974,
      "grad_norm": 0.1233903169631958,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.9286,
      "step": 32
    },
    {
      "epoch": 0.005648267008985879,
      "grad_norm": 0.12037648260593414,
      "learning_rate": 9.871850323926177e-05,
      "loss": 1.982,
      "step": 33
    },
    {
      "epoch": 0.005819426615318785,
      "grad_norm": 0.10984398424625397,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.7714,
      "step": 34
    },
    {
      "epoch": 0.00599058622165169,
      "grad_norm": 0.12199705094099045,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.9782,
      "step": 35
    },
    {
      "epoch": 0.0061617458279845955,
      "grad_norm": 0.12401176989078522,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.08,
      "step": 36
    },
    {
      "epoch": 0.006332905434317501,
      "grad_norm": 0.12610073387622833,
      "learning_rate": 9.781523779815179e-05,
      "loss": 1.9806,
      "step": 37
    },
    {
      "epoch": 0.0065040650406504065,
      "grad_norm": 0.1307840496301651,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1165,
      "step": 38
    },
    {
      "epoch": 0.006675224646983312,
      "grad_norm": 0.13169904053211212,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.9079,
      "step": 39
    },
    {
      "epoch": 0.0068463842533162175,
      "grad_norm": 0.13578273355960846,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.8204,
      "step": 40
    },
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 0.14357295632362366,
      "learning_rate": 9.667902132486009e-05,
      "loss": 1.9466,
      "step": 41
    },
    {
      "epoch": 0.007188703465982028,
      "grad_norm": 0.14602960646152496,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.8532,
      "step": 42
    },
    {
      "epoch": 0.007359863072314934,
      "grad_norm": 0.16406601667404175,
      "learning_rate": 9.602524267262203e-05,
      "loss": 2.0449,
      "step": 43
    },
    {
      "epoch": 0.007531022678647839,
      "grad_norm": 0.1651465892791748,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.083,
      "step": 44
    },
    {
      "epoch": 0.007702182284980745,
      "grad_norm": 0.17137831449508667,
      "learning_rate": 9.53153893518325e-05,
      "loss": 2.0343,
      "step": 45
    },
    {
      "epoch": 0.00787334189131365,
      "grad_norm": 0.18124830722808838,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.8729,
      "step": 46
    },
    {
      "epoch": 0.008044501497646555,
      "grad_norm": 0.22116567194461823,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.8739,
      "step": 47
    },
    {
      "epoch": 0.008215661103979461,
      "grad_norm": 0.28191742300987244,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.0994,
      "step": 48
    },
    {
      "epoch": 0.008386820710312366,
      "grad_norm": 0.6001160144805908,
      "learning_rate": 9.373098535696979e-05,
      "loss": 2.1811,
      "step": 49
    },
    {
      "epoch": 0.008557980316645272,
      "grad_norm": 0.741450309753418,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.1858,
      "step": 50
    },
    {
      "epoch": 0.008557980316645272,
      "eval_loss": 2.0050954818725586,
      "eval_runtime": 259.0142,
      "eval_samples_per_second": 37.99,
      "eval_steps_per_second": 18.995,
      "step": 50
    },
    {
      "epoch": 0.008729139922978177,
      "grad_norm": 0.22430455684661865,
      "learning_rate": 9.285836503510562e-05,
      "loss": 1.8785,
      "step": 51
    },
    {
      "epoch": 0.008900299529311083,
      "grad_norm": 0.20247997343540192,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.9007,
      "step": 52
    },
    {
      "epoch": 0.009071459135643988,
      "grad_norm": 0.18127155303955078,
      "learning_rate": 9.193352839727121e-05,
      "loss": 1.9556,
      "step": 53
    },
    {
      "epoch": 0.009242618741976894,
      "grad_norm": 0.1620718389749527,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.8055,
      "step": 54
    },
    {
      "epoch": 0.009413778348309799,
      "grad_norm": 0.16836689412593842,
      "learning_rate": 9.09576022144496e-05,
      "loss": 1.7112,
      "step": 55
    },
    {
      "epoch": 0.009584937954642705,
      "grad_norm": 0.15607057511806488,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7295,
      "step": 56
    },
    {
      "epoch": 0.00975609756097561,
      "grad_norm": 0.15433867275714874,
      "learning_rate": 8.993177550236464e-05,
      "loss": 1.7898,
      "step": 57
    },
    {
      "epoch": 0.009927257167308514,
      "grad_norm": 0.1581793874502182,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.8115,
      "step": 58
    },
    {
      "epoch": 0.01009841677364142,
      "grad_norm": 0.1593821793794632,
      "learning_rate": 8.885729807284856e-05,
      "loss": 1.8821,
      "step": 59
    },
    {
      "epoch": 0.010269576379974325,
      "grad_norm": 0.13692297041416168,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.9019,
      "step": 60
    },
    {
      "epoch": 0.010440735986307232,
      "grad_norm": 0.13366976380348206,
      "learning_rate": 8.773547901113862e-05,
      "loss": 1.8569,
      "step": 61
    },
    {
      "epoch": 0.010611895592640136,
      "grad_norm": 0.13981181383132935,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.0179,
      "step": 62
    },
    {
      "epoch": 0.010783055198973043,
      "grad_norm": 0.11422371119260788,
      "learning_rate": 8.656768508095853e-05,
      "loss": 1.9594,
      "step": 63
    },
    {
      "epoch": 0.010954214805305947,
      "grad_norm": 0.12120245397090912,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.9958,
      "step": 64
    },
    {
      "epoch": 0.011125374411638854,
      "grad_norm": 0.10169228911399841,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9392,
      "step": 65
    },
    {
      "epoch": 0.011296534017971758,
      "grad_norm": 0.09632351249456406,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.8104,
      "step": 66
    },
    {
      "epoch": 0.011467693624304665,
      "grad_norm": 0.10891255736351013,
      "learning_rate": 8.409991800312493e-05,
      "loss": 2.1084,
      "step": 67
    },
    {
      "epoch": 0.01163885323063757,
      "grad_norm": 0.09422247111797333,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.8242,
      "step": 68
    },
    {
      "epoch": 0.011810012836970476,
      "grad_norm": 0.097730353474617,
      "learning_rate": 8.280295144952536e-05,
      "loss": 1.8866,
      "step": 69
    },
    {
      "epoch": 0.01198117244330338,
      "grad_norm": 0.0988590195775032,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.0188,
      "step": 70
    },
    {
      "epoch": 0.012152332049636286,
      "grad_norm": 0.09687261283397675,
      "learning_rate": 8.146601955249188e-05,
      "loss": 1.9782,
      "step": 71
    },
    {
      "epoch": 0.012323491655969191,
      "grad_norm": 0.10483600199222565,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.9285,
      "step": 72
    },
    {
      "epoch": 0.012494651262302097,
      "grad_norm": 0.10860675573348999,
      "learning_rate": 8.009075115760243e-05,
      "loss": 1.9643,
      "step": 73
    },
    {
      "epoch": 0.012665810868635002,
      "grad_norm": 0.10306871682405472,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.8897,
      "step": 74
    },
    {
      "epoch": 0.012836970474967908,
      "grad_norm": 0.09955226629972458,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.9064,
      "step": 75
    },
    {
      "epoch": 0.013008130081300813,
      "grad_norm": 0.11086455732584,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.9856,
      "step": 76
    },
    {
      "epoch": 0.013179289687633718,
      "grad_norm": 0.106622114777565,
      "learning_rate": 7.723195175075136e-05,
      "loss": 1.9768,
      "step": 77
    },
    {
      "epoch": 0.013350449293966624,
      "grad_norm": 0.11136943846940994,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.0076,
      "step": 78
    },
    {
      "epoch": 0.013521608900299529,
      "grad_norm": 0.10378699749708176,
      "learning_rate": 7.575190374550272e-05,
      "loss": 2.0183,
      "step": 79
    },
    {
      "epoch": 0.013692768506632435,
      "grad_norm": 0.10002272576093674,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.9106,
      "step": 80
    },
    {
      "epoch": 0.01386392811296534,
      "grad_norm": 0.10468745976686478,
      "learning_rate": 7.424048101231686e-05,
      "loss": 2.1109,
      "step": 81
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 0.1047583818435669,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.8169,
      "step": 82
    },
    {
      "epoch": 0.01420624732563115,
      "grad_norm": 0.11088533699512482,
      "learning_rate": 7.269952498697734e-05,
      "loss": 2.0148,
      "step": 83
    },
    {
      "epoch": 0.014377406931964057,
      "grad_norm": 0.11189869791269302,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.9053,
      "step": 84
    },
    {
      "epoch": 0.014548566538296961,
      "grad_norm": 0.11222604662179947,
      "learning_rate": 7.113091308703498e-05,
      "loss": 1.85,
      "step": 85
    },
    {
      "epoch": 0.014719726144629868,
      "grad_norm": 0.11671954393386841,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.8606,
      "step": 86
    },
    {
      "epoch": 0.014890885750962772,
      "grad_norm": 0.11258739233016968,
      "learning_rate": 6.953655642446368e-05,
      "loss": 1.9892,
      "step": 87
    },
    {
      "epoch": 0.015062045357295679,
      "grad_norm": 0.12018974870443344,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.0688,
      "step": 88
    },
    {
      "epoch": 0.015233204963628583,
      "grad_norm": 0.1348743736743927,
      "learning_rate": 6.7918397477265e-05,
      "loss": 1.9919,
      "step": 89
    },
    {
      "epoch": 0.01540436456996149,
      "grad_norm": 0.13200099766254425,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.9153,
      "step": 90
    },
    {
      "epoch": 0.015575524176294394,
      "grad_norm": 0.1338081955909729,
      "learning_rate": 6.627840772285784e-05,
      "loss": 1.7685,
      "step": 91
    },
    {
      "epoch": 0.0157466837826273,
      "grad_norm": 0.13655497133731842,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9897,
      "step": 92
    },
    {
      "epoch": 0.015917843388960205,
      "grad_norm": 0.1462564319372177,
      "learning_rate": 6.461858523613684e-05,
      "loss": 1.692,
      "step": 93
    },
    {
      "epoch": 0.01608900299529311,
      "grad_norm": 0.16037926077842712,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.9882,
      "step": 94
    },
    {
      "epoch": 0.016260162601626018,
      "grad_norm": 0.16777467727661133,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.8377,
      "step": 95
    },
    {
      "epoch": 0.016431322207958923,
      "grad_norm": 0.21440783143043518,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.9863,
      "step": 96
    },
    {
      "epoch": 0.016602481814291827,
      "grad_norm": 0.23396961390972137,
      "learning_rate": 6.124755271719325e-05,
      "loss": 2.1281,
      "step": 97
    },
    {
      "epoch": 0.016773641420624732,
      "grad_norm": 0.29652488231658936,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.373,
      "step": 98
    },
    {
      "epoch": 0.016944801026957636,
      "grad_norm": 0.403049498796463,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 2.1079,
      "step": 99
    },
    {
      "epoch": 0.017115960633290545,
      "grad_norm": 0.7542735934257507,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.4682,
      "step": 100
    },
    {
      "epoch": 0.017115960633290545,
      "eval_loss": 1.9593321084976196,
      "eval_runtime": 259.8209,
      "eval_samples_per_second": 37.872,
      "eval_steps_per_second": 18.936,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3850414190493696.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}