{
  "best_metric": 0.011846823617815971,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.05767567047966932,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005767567047966932,
      "grad_norm": 3.5087673664093018,
      "learning_rate": 2e-05,
      "loss": 0.9661,
      "step": 1
    },
    {
      "epoch": 0.0005767567047966932,
      "eval_loss": 0.256265789270401,
      "eval_runtime": 215.9962,
      "eval_samples_per_second": 8.028,
      "eval_steps_per_second": 2.009,
      "step": 1
    },
    {
      "epoch": 0.0011535134095933864,
      "grad_norm": 5.137994289398193,
      "learning_rate": 4e-05,
      "loss": 1.1907,
      "step": 2
    },
    {
      "epoch": 0.0017302701143900798,
      "grad_norm": 6.508111000061035,
      "learning_rate": 6e-05,
      "loss": 1.3703,
      "step": 3
    },
    {
      "epoch": 0.002307026819186773,
      "grad_norm": 2.984405040740967,
      "learning_rate": 8e-05,
      "loss": 0.7919,
      "step": 4
    },
    {
      "epoch": 0.0028837835239834664,
      "grad_norm": 6.96499490737915,
      "learning_rate": 0.0001,
      "loss": 1.5441,
      "step": 5
    },
    {
      "epoch": 0.0034605402287801595,
      "grad_norm": 5.478267192840576,
      "learning_rate": 0.00012,
      "loss": 0.7325,
      "step": 6
    },
    {
      "epoch": 0.004037296933576853,
      "grad_norm": 2.7913830280303955,
      "learning_rate": 0.00014,
      "loss": 0.4881,
      "step": 7
    },
    {
      "epoch": 0.004614053638373546,
      "grad_norm": 3.1158297061920166,
      "learning_rate": 0.00016,
      "loss": 0.2994,
      "step": 8
    },
    {
      "epoch": 0.005190810343170239,
      "grad_norm": 3.412966012954712,
      "learning_rate": 0.00018,
      "loss": 0.2548,
      "step": 9
    },
    {
      "epoch": 0.005767567047966933,
      "grad_norm": 3.8502895832061768,
      "learning_rate": 0.0002,
      "loss": 0.1836,
      "step": 10
    },
    {
      "epoch": 0.0063443237527636255,
      "grad_norm": 2.5958235263824463,
      "learning_rate": 0.00019999852288943748,
      "loss": 0.0852,
      "step": 11
    },
    {
      "epoch": 0.006921080457560319,
      "grad_norm": 4.420118808746338,
      "learning_rate": 0.00019999409160138693,
      "loss": 0.1172,
      "step": 12
    },
    {
      "epoch": 0.007497837162357013,
      "grad_norm": 2.869602918624878,
      "learning_rate": 0.00019998670626675846,
      "loss": 0.051,
      "step": 13
    },
    {
      "epoch": 0.008074593867153706,
      "grad_norm": 1.1618932485580444,
      "learning_rate": 0.0001999763671037312,
      "loss": 0.0148,
      "step": 14
    },
    {
      "epoch": 0.008651350571950399,
      "grad_norm": 4.91132116317749,
      "learning_rate": 0.00019996307441774684,
      "loss": 0.0444,
      "step": 15
    },
    {
      "epoch": 0.009228107276747092,
      "grad_norm": 1.5534745454788208,
      "learning_rate": 0.00019994682860150073,
      "loss": 0.0288,
      "step": 16
    },
    {
      "epoch": 0.009804863981543786,
      "grad_norm": 2.5079476833343506,
      "learning_rate": 0.0001999276301349302,
      "loss": 0.0389,
      "step": 17
    },
    {
      "epoch": 0.010381620686340479,
      "grad_norm": 2.015561580657959,
      "learning_rate": 0.00019990547958520044,
      "loss": 0.0538,
      "step": 18
    },
    {
      "epoch": 0.010958377391137171,
      "grad_norm": 0.5642620325088501,
      "learning_rate": 0.00019988037760668766,
      "loss": 0.0044,
      "step": 19
    },
    {
      "epoch": 0.011535134095933866,
      "grad_norm": 1.0824285745620728,
      "learning_rate": 0.0001998523249409598,
      "loss": 0.0099,
      "step": 20
    },
    {
      "epoch": 0.012111890800730558,
      "grad_norm": 1.1586933135986328,
      "learning_rate": 0.00019982132241675463,
      "loss": 0.0149,
      "step": 21
    },
    {
      "epoch": 0.012688647505527251,
      "grad_norm": 1.043748378753662,
      "learning_rate": 0.00019978737094995526,
      "loss": 0.0111,
      "step": 22
    },
    {
      "epoch": 0.013265404210323945,
      "grad_norm": 1.1925742626190186,
      "learning_rate": 0.0001997504715435631,
      "loss": 0.0212,
      "step": 23
    },
    {
      "epoch": 0.013842160915120638,
      "grad_norm": 4.5300445556640625,
      "learning_rate": 0.00019971062528766824,
      "loss": 0.0469,
      "step": 24
    },
    {
      "epoch": 0.01441891761991733,
      "grad_norm": 1.0790067911148071,
      "learning_rate": 0.00019966783335941717,
      "loss": 0.026,
      "step": 25
    },
    {
      "epoch": 0.014995674324714025,
      "grad_norm": 0.853151798248291,
      "learning_rate": 0.00019962209702297808,
      "loss": 0.0242,
      "step": 26
    },
    {
      "epoch": 0.015572431029510718,
      "grad_norm": 1.722130537033081,
      "learning_rate": 0.00019957341762950344,
      "loss": 0.0478,
      "step": 27
    },
    {
      "epoch": 0.016149187734307412,
      "grad_norm": 2.9154410362243652,
      "learning_rate": 0.00019952179661709028,
      "loss": 0.0796,
      "step": 28
    },
    {
      "epoch": 0.016725944439104103,
      "grad_norm": 1.8094756603240967,
      "learning_rate": 0.00019946723551073732,
      "loss": 0.0222,
      "step": 29
    },
    {
      "epoch": 0.017302701143900798,
      "grad_norm": 2.117493152618408,
      "learning_rate": 0.0001994097359223004,
      "loss": 0.0215,
      "step": 30
    },
    {
      "epoch": 0.017879457848697492,
      "grad_norm": 0.26287028193473816,
      "learning_rate": 0.0001993492995504444,
      "loss": 0.0066,
      "step": 31
    },
    {
      "epoch": 0.018456214553494183,
      "grad_norm": 30.89515495300293,
      "learning_rate": 0.0001992859281805935,
      "loss": 0.0778,
      "step": 32
    },
    {
      "epoch": 0.019032971258290877,
      "grad_norm": 4.260768413543701,
      "learning_rate": 0.00019921962368487807,
      "loss": 0.0816,
      "step": 33
    },
    {
      "epoch": 0.019609727963087572,
      "grad_norm": 1.1326998472213745,
      "learning_rate": 0.00019915038802207944,
      "loss": 0.0209,
      "step": 34
    },
    {
      "epoch": 0.020186484667884263,
      "grad_norm": 4.575008869171143,
      "learning_rate": 0.00019907822323757225,
      "loss": 0.1154,
      "step": 35
    },
    {
      "epoch": 0.020763241372680957,
      "grad_norm": 5.928327560424805,
      "learning_rate": 0.00019900313146326384,
      "loss": 0.2387,
      "step": 36
    },
    {
      "epoch": 0.02133999807747765,
      "grad_norm": 21.27695655822754,
      "learning_rate": 0.00019892511491753124,
      "loss": 0.202,
      "step": 37
    },
    {
      "epoch": 0.021916754782274343,
      "grad_norm": 3.236907482147217,
      "learning_rate": 0.00019884417590515573,
      "loss": 0.1093,
      "step": 38
    },
    {
      "epoch": 0.022493511487071037,
      "grad_norm": 2.1399052143096924,
      "learning_rate": 0.00019876031681725467,
      "loss": 0.0944,
      "step": 39
    },
    {
      "epoch": 0.02307026819186773,
      "grad_norm": 3.7547476291656494,
      "learning_rate": 0.000198673540131211,
      "loss": 0.1158,
      "step": 40
    },
    {
      "epoch": 0.023647024896664422,
      "grad_norm": 2.028630256652832,
      "learning_rate": 0.0001985838484105999,
      "loss": 0.062,
      "step": 41
    },
    {
      "epoch": 0.024223781601461117,
      "grad_norm": 1.1861765384674072,
      "learning_rate": 0.0001984912443051131,
      "loss": 0.0637,
      "step": 42
    },
    {
      "epoch": 0.02480053830625781,
      "grad_norm": 4.997815132141113,
      "learning_rate": 0.0001983957305504807,
      "loss": 0.0905,
      "step": 43
    },
    {
      "epoch": 0.025377295011054502,
      "grad_norm": 3.761312484741211,
      "learning_rate": 0.0001982973099683902,
      "loss": 0.0537,
      "step": 44
    },
    {
      "epoch": 0.025954051715851197,
      "grad_norm": 8.485271453857422,
      "learning_rate": 0.0001981959854664032,
      "loss": 0.2039,
      "step": 45
    },
    {
      "epoch": 0.02653080842064789,
      "grad_norm": 4.167719841003418,
      "learning_rate": 0.00019809176003786954,
      "loss": 0.1507,
      "step": 46
    },
    {
      "epoch": 0.027107565125444582,
      "grad_norm": 13.948970794677734,
      "learning_rate": 0.00019798463676183888,
      "loss": 0.0811,
      "step": 47
    },
    {
      "epoch": 0.027684321830241276,
      "grad_norm": 16.908702850341797,
      "learning_rate": 0.00019787461880296965,
      "loss": 0.2963,
      "step": 48
    },
    {
      "epoch": 0.02826107853503797,
      "grad_norm": 2.1487314701080322,
      "learning_rate": 0.00019776170941143565,
      "loss": 0.0582,
      "step": 49
    },
    {
      "epoch": 0.02883783523983466,
      "grad_norm": 3.16274356842041,
      "learning_rate": 0.00019764591192282993,
      "loss": 0.0622,
      "step": 50
    },
    {
      "epoch": 0.029414591944631356,
      "grad_norm": 2.1081337928771973,
      "learning_rate": 0.0001975272297580664,
      "loss": 0.1675,
      "step": 51
    },
    {
      "epoch": 0.02999134864942805,
      "grad_norm": 1.3357646465301514,
      "learning_rate": 0.00019740566642327867,
      "loss": 0.0394,
      "step": 52
    },
    {
      "epoch": 0.03056810535422474,
      "grad_norm": 2.5485501289367676,
      "learning_rate": 0.00019728122550971642,
      "loss": 0.1227,
      "step": 53
    },
    {
      "epoch": 0.031144862059021436,
      "grad_norm": 7.7235870361328125,
      "learning_rate": 0.0001971539106936394,
      "loss": 0.1759,
      "step": 54
    },
    {
      "epoch": 0.03172161876381813,
      "grad_norm": 5.811506748199463,
      "learning_rate": 0.00019702372573620881,
      "loss": 0.1152,
      "step": 55
    },
    {
      "epoch": 0.032298375468614825,
      "grad_norm": 1.4860045909881592,
      "learning_rate": 0.00019689067448337618,
      "loss": 0.0469,
      "step": 56
    },
    {
      "epoch": 0.032875132173411516,
      "grad_norm": 1.4226983785629272,
      "learning_rate": 0.00019675476086576972,
      "loss": 0.0395,
      "step": 57
    },
    {
      "epoch": 0.03345188887820821,
      "grad_norm": 0.34651094675064087,
      "learning_rate": 0.0001966159888985782,
      "loss": 0.0185,
      "step": 58
    },
    {
      "epoch": 0.034028645583004904,
      "grad_norm": 0.8589548468589783,
      "learning_rate": 0.00019647436268143247,
      "loss": 0.0172,
      "step": 59
    },
    {
      "epoch": 0.034605402287801595,
      "grad_norm": 1.4422504901885986,
      "learning_rate": 0.00019632988639828406,
      "loss": 0.0369,
      "step": 60
    },
    {
      "epoch": 0.035182158992598286,
      "grad_norm": 2.7948107719421387,
      "learning_rate": 0.00019618256431728194,
      "loss": 0.0839,
      "step": 61
    },
    {
      "epoch": 0.035758915697394984,
      "grad_norm": 0.973739743232727,
      "learning_rate": 0.00019603240079064604,
      "loss": 0.0967,
      "step": 62
    },
    {
      "epoch": 0.036335672402191675,
      "grad_norm": 1.0291193723678589,
      "learning_rate": 0.00019587940025453908,
      "loss": 0.0121,
      "step": 63
    },
    {
      "epoch": 0.036912429106988366,
      "grad_norm": 3.7419233322143555,
      "learning_rate": 0.00019572356722893518,
      "loss": 0.0257,
      "step": 64
    },
    {
      "epoch": 0.037489185811785064,
      "grad_norm": 0.9348726868629456,
      "learning_rate": 0.00019556490631748651,
      "loss": 0.0038,
      "step": 65
    },
    {
      "epoch": 0.038065942516581755,
      "grad_norm": 2.067941904067993,
      "learning_rate": 0.00019540342220738724,
      "loss": 0.011,
      "step": 66
    },
    {
      "epoch": 0.038642699221378446,
      "grad_norm": 5.878370761871338,
      "learning_rate": 0.00019523911966923507,
      "loss": 0.0176,
      "step": 67
    },
    {
      "epoch": 0.039219455926175144,
      "grad_norm": 2.2632899284362793,
      "learning_rate": 0.00019507200355689026,
      "loss": 0.0224,
      "step": 68
    },
    {
      "epoch": 0.039796212630971835,
      "grad_norm": 3.178539752960205,
      "learning_rate": 0.00019490207880733232,
      "loss": 0.0314,
      "step": 69
    },
    {
      "epoch": 0.040372969335768526,
      "grad_norm": 1.259251594543457,
      "learning_rate": 0.0001947293504405141,
      "loss": 0.0035,
      "step": 70
    },
    {
      "epoch": 0.040949726040565224,
      "grad_norm": 0.4863012433052063,
      "learning_rate": 0.00019455382355921353,
      "loss": 0.0102,
      "step": 71
    },
    {
      "epoch": 0.041526482745361915,
      "grad_norm": 52.19420623779297,
      "learning_rate": 0.00019437550334888278,
      "loss": 0.1446,
      "step": 72
    },
    {
      "epoch": 0.042103239450158605,
      "grad_norm": 1.488041639328003,
      "learning_rate": 0.00019419439507749515,
      "loss": 0.0246,
      "step": 73
    },
    {
      "epoch": 0.0426799961549553,
      "grad_norm": 0.3983250856399536,
      "learning_rate": 0.0001940105040953895,
      "loss": 0.0038,
      "step": 74
    },
    {
      "epoch": 0.043256752859751994,
      "grad_norm": 1.9497828483581543,
      "learning_rate": 0.00019382383583511206,
      "loss": 0.0124,
      "step": 75
    },
    {
      "epoch": 0.043833509564548685,
      "grad_norm": 5.796697616577148,
      "learning_rate": 0.00019363439581125601,
      "loss": 0.0264,
      "step": 76
    },
    {
      "epoch": 0.04441026626934538,
      "grad_norm": 4.687071323394775,
      "learning_rate": 0.00019344218962029857,
      "loss": 0.017,
      "step": 77
    },
    {
      "epoch": 0.044987022974142074,
      "grad_norm": 3.4617161750793457,
      "learning_rate": 0.00019324722294043558,
      "loss": 0.0973,
      "step": 78
    },
    {
      "epoch": 0.045563779678938765,
      "grad_norm": 1.2890996932983398,
      "learning_rate": 0.00019304950153141393,
      "loss": 0.0152,
      "step": 79
    },
    {
      "epoch": 0.04614053638373546,
      "grad_norm": 2.0128302574157715,
      "learning_rate": 0.00019284903123436127,
      "loss": 0.035,
      "step": 80
    },
    {
      "epoch": 0.046717293088532154,
      "grad_norm": 0.14461462199687958,
      "learning_rate": 0.00019264581797161343,
      "loss": 0.004,
      "step": 81
    },
    {
      "epoch": 0.047294049793328845,
      "grad_norm": 0.43382060527801514,
      "learning_rate": 0.00019243986774653956,
      "loss": 0.0044,
      "step": 82
    },
    {
      "epoch": 0.04787080649812554,
      "grad_norm": 0.5092380046844482,
      "learning_rate": 0.00019223118664336467,
      "loss": 0.0032,
      "step": 83
    },
    {
      "epoch": 0.048447563202922234,
      "grad_norm": 0.5211856365203857,
      "learning_rate": 0.0001920197808269901,
      "loss": 0.0059,
      "step": 84
    },
    {
      "epoch": 0.049024319907718925,
      "grad_norm": 1.6433213949203491,
      "learning_rate": 0.00019180565654281103,
      "loss": 0.1625,
      "step": 85
    },
    {
      "epoch": 0.04960107661251562,
      "grad_norm": 2.427119016647339,
      "learning_rate": 0.00019158882011653235,
      "loss": 0.0246,
      "step": 86
    },
    {
      "epoch": 0.05017783331731231,
      "grad_norm": 0.8261755108833313,
      "learning_rate": 0.00019136927795398157,
      "loss": 0.0113,
      "step": 87
    },
    {
      "epoch": 0.050754590022109004,
      "grad_norm": 0.15122078359127045,
      "learning_rate": 0.00019114703654091961,
      "loss": 0.005,
      "step": 88
    },
    {
      "epoch": 0.0513313467269057,
      "grad_norm": 0.5468443632125854,
      "learning_rate": 0.00019092210244284926,
      "loss": 0.017,
      "step": 89
    },
    {
      "epoch": 0.05190810343170239,
      "grad_norm": 0.640923798084259,
      "learning_rate": 0.00019069448230482118,
      "loss": 0.0323,
      "step": 90
    },
    {
      "epoch": 0.052484860136499084,
      "grad_norm": 0.2306308001279831,
      "learning_rate": 0.00019046418285123754,
      "loss": 0.0039,
      "step": 91
    },
    {
      "epoch": 0.05306161684129578,
      "grad_norm": 0.3201711177825928,
      "learning_rate": 0.00019023121088565352,
      "loss": 0.0037,
      "step": 92
    },
    {
      "epoch": 0.05363837354609247,
      "grad_norm": 1.7555040121078491,
      "learning_rate": 0.00018999557329057605,
      "loss": 0.0232,
      "step": 93
    },
    {
      "epoch": 0.054215130250889164,
      "grad_norm": 0.04883858934044838,
      "learning_rate": 0.00018975727702726076,
      "loss": 0.0016,
      "step": 94
    },
    {
      "epoch": 0.05479188695568586,
      "grad_norm": 0.11811670660972595,
      "learning_rate": 0.00018951632913550626,
      "loss": 0.0031,
      "step": 95
    },
    {
      "epoch": 0.05536864366048255,
      "grad_norm": 0.3842681050300598,
      "learning_rate": 0.000189272736733446,
      "loss": 0.0032,
      "step": 96
    },
    {
      "epoch": 0.055945400365279244,
      "grad_norm": 0.34558194875717163,
      "learning_rate": 0.0001890265070173382,
      "loss": 0.0041,
      "step": 97
    },
    {
      "epoch": 0.05652215707007594,
      "grad_norm": 0.23080027103424072,
      "learning_rate": 0.0001887776472613532,
      "loss": 0.0052,
      "step": 98
    },
    {
      "epoch": 0.05709891377487263,
      "grad_norm": 0.8554419875144958,
      "learning_rate": 0.00018852616481735841,
      "loss": 0.0142,
      "step": 99
    },
    {
      "epoch": 0.05767567047966932,
      "grad_norm": 0.6974347233772278,
      "learning_rate": 0.00018827206711470137,
      "loss": 0.0136,
      "step": 100
    },
    {
      "epoch": 0.05767567047966932,
      "eval_loss": 0.011846823617815971,
      "eval_runtime": 218.0508,
      "eval_samples_per_second": 7.952,
      "eval_steps_per_second": 1.99,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 588,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "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": 2.0888783655901594e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}