{
  "best_metric": 0.12831655144691467,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.11242665917155606,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011242665917155605,
      "grad_norm": 0.6658321619033813,
      "learning_rate": 2e-05,
      "loss": 0.2297,
      "step": 1
    },
    {
      "epoch": 0.0011242665917155605,
      "eval_loss": 0.4750947654247284,
      "eval_runtime": 1.1152,
      "eval_samples_per_second": 44.836,
      "eval_steps_per_second": 11.657,
      "step": 1
    },
    {
      "epoch": 0.002248533183431121,
      "grad_norm": 0.9659503102302551,
      "learning_rate": 4e-05,
      "loss": 0.2872,
      "step": 2
    },
    {
      "epoch": 0.0033727997751466818,
      "grad_norm": 1.0396761894226074,
      "learning_rate": 6e-05,
      "loss": 0.3116,
      "step": 3
    },
    {
      "epoch": 0.004497066366862242,
      "grad_norm": 0.7709479331970215,
      "learning_rate": 8e-05,
      "loss": 0.2604,
      "step": 4
    },
    {
      "epoch": 0.005621332958577803,
      "grad_norm": 0.5585924983024597,
      "learning_rate": 0.0001,
      "loss": 0.2226,
      "step": 5
    },
    {
      "epoch": 0.0067455995502933635,
      "grad_norm": 0.5157190561294556,
      "learning_rate": 9.997539658034168e-05,
      "loss": 0.2107,
      "step": 6
    },
    {
      "epoch": 0.007869866142008923,
      "grad_norm": 0.5248725414276123,
      "learning_rate": 9.990161322484486e-05,
      "loss": 0.2093,
      "step": 7
    },
    {
      "epoch": 0.008994132733724484,
      "grad_norm": 0.3566325604915619,
      "learning_rate": 9.977873061452552e-05,
      "loss": 0.2123,
      "step": 8
    },
    {
      "epoch": 0.010118399325440045,
      "grad_norm": 0.293720006942749,
      "learning_rate": 9.96068831197139e-05,
      "loss": 0.2024,
      "step": 9
    },
    {
      "epoch": 0.011242665917155606,
      "grad_norm": 0.3009275496006012,
      "learning_rate": 9.938625865312251e-05,
      "loss": 0.2009,
      "step": 10
    },
    {
      "epoch": 0.012366932508871166,
      "grad_norm": 0.31864267587661743,
      "learning_rate": 9.911709846436641e-05,
      "loss": 0.1929,
      "step": 11
    },
    {
      "epoch": 0.013491199100586727,
      "grad_norm": 0.3316473662853241,
      "learning_rate": 9.879969687616027e-05,
      "loss": 0.1681,
      "step": 12
    },
    {
      "epoch": 0.014615465692302288,
      "grad_norm": 0.18495744466781616,
      "learning_rate": 9.84344009624807e-05,
      "loss": 0.1454,
      "step": 13
    },
    {
      "epoch": 0.015739732284017847,
      "grad_norm": 0.15138748288154602,
      "learning_rate": 9.80216101690461e-05,
      "loss": 0.141,
      "step": 14
    },
    {
      "epoch": 0.016863998875733408,
      "grad_norm": 0.17268440127372742,
      "learning_rate": 9.756177587652856e-05,
      "loss": 0.1498,
      "step": 15
    },
    {
      "epoch": 0.017988265467448968,
      "grad_norm": 0.1772288978099823,
      "learning_rate": 9.705540090697575e-05,
      "loss": 0.1583,
      "step": 16
    },
    {
      "epoch": 0.01911253205916453,
      "grad_norm": 0.18687909841537476,
      "learning_rate": 9.650303897398232e-05,
      "loss": 0.1729,
      "step": 17
    },
    {
      "epoch": 0.02023679865088009,
      "grad_norm": 0.17860423028469086,
      "learning_rate": 9.590529407721231e-05,
      "loss": 0.1472,
      "step": 18
    },
    {
      "epoch": 0.02136106524259565,
      "grad_norm": 0.18536882102489471,
      "learning_rate": 9.526281984193436e-05,
      "loss": 0.163,
      "step": 19
    },
    {
      "epoch": 0.02248533183431121,
      "grad_norm": 0.19355811178684235,
      "learning_rate": 9.4576318804292e-05,
      "loss": 0.1727,
      "step": 20
    },
    {
      "epoch": 0.023609598426026772,
      "grad_norm": 0.3388013541698456,
      "learning_rate": 9.384654164309083e-05,
      "loss": 0.1562,
      "step": 21
    },
    {
      "epoch": 0.024733865017742333,
      "grad_norm": 0.20482496917247772,
      "learning_rate": 9.30742863589421e-05,
      "loss": 0.1502,
      "step": 22
    },
    {
      "epoch": 0.025858131609457893,
      "grad_norm": 0.2337004542350769,
      "learning_rate": 9.226039740166091e-05,
      "loss": 0.1712,
      "step": 23
    },
    {
      "epoch": 0.026982398201173454,
      "grad_norm": 0.2403237372636795,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.1597,
      "step": 24
    },
    {
      "epoch": 0.028106664792889015,
      "grad_norm": 0.4346703886985779,
      "learning_rate": 9.051132292283771e-05,
      "loss": 0.2227,
      "step": 25
    },
    {
      "epoch": 0.028106664792889015,
      "eval_loss": 0.14181500673294067,
      "eval_runtime": 1.1135,
      "eval_samples_per_second": 44.902,
      "eval_steps_per_second": 11.675,
      "step": 25
    },
    {
      "epoch": 0.029230931384604576,
      "grad_norm": 0.1223050057888031,
      "learning_rate": 8.957804998855866e-05,
      "loss": 0.129,
      "step": 26
    },
    {
      "epoch": 0.030355197976320136,
      "grad_norm": 0.14993822574615479,
      "learning_rate": 8.860696646428693e-05,
      "loss": 0.151,
      "step": 27
    },
    {
      "epoch": 0.031479464568035694,
      "grad_norm": 0.14519862830638885,
      "learning_rate": 8.759913421559902e-05,
      "loss": 0.1472,
      "step": 28
    },
    {
      "epoch": 0.03260373115975126,
      "grad_norm": 0.14449714124202728,
      "learning_rate": 8.655565529226198e-05,
      "loss": 0.1407,
      "step": 29
    },
    {
      "epoch": 0.033727997751466815,
      "grad_norm": 0.15906383097171783,
      "learning_rate": 8.547767072315835e-05,
      "loss": 0.1488,
      "step": 30
    },
    {
      "epoch": 0.03485226434318238,
      "grad_norm": 0.1723470389842987,
      "learning_rate": 8.436635926858759e-05,
      "loss": 0.1589,
      "step": 31
    },
    {
      "epoch": 0.035976530934897936,
      "grad_norm": 0.17348530888557434,
      "learning_rate": 8.322293613130917e-05,
      "loss": 0.1556,
      "step": 32
    },
    {
      "epoch": 0.0371007975266135,
      "grad_norm": 0.18658830225467682,
      "learning_rate": 8.204865162773613e-05,
      "loss": 0.1504,
      "step": 33
    },
    {
      "epoch": 0.03822506411832906,
      "grad_norm": 0.18366535007953644,
      "learning_rate": 8.084478982073247e-05,
      "loss": 0.1579,
      "step": 34
    },
    {
      "epoch": 0.03934933071004462,
      "grad_norm": 0.21894170343875885,
      "learning_rate": 7.961266711550922e-05,
      "loss": 0.1663,
      "step": 35
    },
    {
      "epoch": 0.04047359730176018,
      "grad_norm": 0.24690447747707367,
      "learning_rate": 7.835363082015468e-05,
      "loss": 0.1927,
      "step": 36
    },
    {
      "epoch": 0.041597863893475744,
      "grad_norm": 0.2482253760099411,
      "learning_rate": 7.706905767237288e-05,
      "loss": 0.1494,
      "step": 37
    },
    {
      "epoch": 0.0427221304851913,
      "grad_norm": 0.14050187170505524,
      "learning_rate": 7.576035233404096e-05,
      "loss": 0.114,
      "step": 38
    },
    {
      "epoch": 0.04384639707690686,
      "grad_norm": 0.13259153068065643,
      "learning_rate": 7.442894585523218e-05,
      "loss": 0.1524,
      "step": 39
    },
    {
      "epoch": 0.04497066366862242,
      "grad_norm": 0.1424197554588318,
      "learning_rate": 7.307629410938363e-05,
      "loss": 0.1407,
      "step": 40
    },
    {
      "epoch": 0.04609493026033798,
      "grad_norm": 0.15291941165924072,
      "learning_rate": 7.170387620131993e-05,
      "loss": 0.154,
      "step": 41
    },
    {
      "epoch": 0.047219196852053544,
      "grad_norm": 0.15763209760189056,
      "learning_rate": 7.031319284987394e-05,
      "loss": 0.167,
      "step": 42
    },
    {
      "epoch": 0.0483434634437691,
      "grad_norm": 0.15876591205596924,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.1551,
      "step": 43
    },
    {
      "epoch": 0.049467730035484665,
      "grad_norm": 0.1577296108007431,
      "learning_rate": 6.7483130894283e-05,
      "loss": 0.1401,
      "step": 44
    },
    {
      "epoch": 0.05059199662720022,
      "grad_norm": 0.17547576129436493,
      "learning_rate": 6.604684692133597e-05,
      "loss": 0.1662,
      "step": 45
    },
    {
      "epoch": 0.05171626321891579,
      "grad_norm": 0.17663820087909698,
      "learning_rate": 6.459848338346861e-05,
      "loss": 0.1652,
      "step": 46
    },
    {
      "epoch": 0.052840529810631344,
      "grad_norm": 0.202792227268219,
      "learning_rate": 6.313962404494496e-05,
      "loss": 0.1564,
      "step": 47
    },
    {
      "epoch": 0.05396479640234691,
      "grad_norm": 0.19537977874279022,
      "learning_rate": 6.167186414703289e-05,
      "loss": 0.139,
      "step": 48
    },
    {
      "epoch": 0.055089062994062465,
      "grad_norm": 0.26559627056121826,
      "learning_rate": 6.019680866363139e-05,
      "loss": 0.1784,
      "step": 49
    },
    {
      "epoch": 0.05621332958577803,
      "grad_norm": 0.35893431305885315,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 0.1805,
      "step": 50
    },
    {
      "epoch": 0.05621332958577803,
      "eval_loss": 0.13392838835716248,
      "eval_runtime": 1.1138,
      "eval_samples_per_second": 44.891,
      "eval_steps_per_second": 11.672,
      "step": 50
    },
    {
      "epoch": 0.05733759617749359,
      "grad_norm": 0.09779861569404602,
      "learning_rate": 5.7231268960295e-05,
      "loss": 0.1136,
      "step": 51
    },
    {
      "epoch": 0.05846186276920915,
      "grad_norm": 0.12952782213687897,
      "learning_rate": 5.574402751448614e-05,
      "loss": 0.1409,
      "step": 52
    },
    {
      "epoch": 0.05958612936092471,
      "grad_norm": 0.14181578159332275,
      "learning_rate": 5.425597248551387e-05,
      "loss": 0.1413,
      "step": 53
    },
    {
      "epoch": 0.06071039595264027,
      "grad_norm": 0.1471935510635376,
      "learning_rate": 5.2768731039705e-05,
      "loss": 0.1423,
      "step": 54
    },
    {
      "epoch": 0.06183466254435583,
      "grad_norm": 0.16710589826107025,
      "learning_rate": 5.128392945374505e-05,
      "loss": 0.1477,
      "step": 55
    },
    {
      "epoch": 0.06295892913607139,
      "grad_norm": 0.1667054444551468,
      "learning_rate": 4.980319133636863e-05,
      "loss": 0.1463,
      "step": 56
    },
    {
      "epoch": 0.06408319572778695,
      "grad_norm": 0.1824021190404892,
      "learning_rate": 4.83281358529671e-05,
      "loss": 0.1623,
      "step": 57
    },
    {
      "epoch": 0.06520746231950252,
      "grad_norm": 0.18960590660572052,
      "learning_rate": 4.686037595505507e-05,
      "loss": 0.1452,
      "step": 58
    },
    {
      "epoch": 0.06633172891121807,
      "grad_norm": 0.19344769418239594,
      "learning_rate": 4.54015166165314e-05,
      "loss": 0.1616,
      "step": 59
    },
    {
      "epoch": 0.06745599550293363,
      "grad_norm": 0.17828473448753357,
      "learning_rate": 4.395315307866405e-05,
      "loss": 0.1266,
      "step": 60
    },
    {
      "epoch": 0.0685802620946492,
      "grad_norm": 0.21599431335926056,
      "learning_rate": 4.2516869105717004e-05,
      "loss": 0.1387,
      "step": 61
    },
    {
      "epoch": 0.06970452868636476,
      "grad_norm": 0.2585263252258301,
      "learning_rate": 4.109423525312738e-05,
      "loss": 0.1556,
      "step": 62
    },
    {
      "epoch": 0.07082879527808031,
      "grad_norm": 0.12306924909353256,
      "learning_rate": 3.968680715012606e-05,
      "loss": 0.1098,
      "step": 63
    },
    {
      "epoch": 0.07195306186979587,
      "grad_norm": 0.11643731594085693,
      "learning_rate": 3.829612379868006e-05,
      "loss": 0.1332,
      "step": 64
    },
    {
      "epoch": 0.07307732846151144,
      "grad_norm": 0.12227363139390945,
      "learning_rate": 3.692370589061639e-05,
      "loss": 0.1248,
      "step": 65
    },
    {
      "epoch": 0.074201595053227,
      "grad_norm": 0.13636033236980438,
      "learning_rate": 3.557105414476782e-05,
      "loss": 0.1518,
      "step": 66
    },
    {
      "epoch": 0.07532586164494255,
      "grad_norm": 0.14901277422904968,
      "learning_rate": 3.423964766595906e-05,
      "loss": 0.1477,
      "step": 67
    },
    {
      "epoch": 0.07645012823665812,
      "grad_norm": 0.14018963277339935,
      "learning_rate": 3.293094232762715e-05,
      "loss": 0.1384,
      "step": 68
    },
    {
      "epoch": 0.07757439482837368,
      "grad_norm": 0.14247332513332367,
      "learning_rate": 3.164636917984534e-05,
      "loss": 0.1249,
      "step": 69
    },
    {
      "epoch": 0.07869866142008924,
      "grad_norm": 0.1646346151828766,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 0.1344,
      "step": 70
    },
    {
      "epoch": 0.0798229280118048,
      "grad_norm": 0.17401055991649628,
      "learning_rate": 2.9155210179267546e-05,
      "loss": 0.1621,
      "step": 71
    },
    {
      "epoch": 0.08094719460352036,
      "grad_norm": 0.1905514895915985,
      "learning_rate": 2.7951348372263875e-05,
      "loss": 0.1265,
      "step": 72
    },
    {
      "epoch": 0.08207146119523592,
      "grad_norm": 0.20102576911449432,
      "learning_rate": 2.677706386869083e-05,
      "loss": 0.1469,
      "step": 73
    },
    {
      "epoch": 0.08319572778695149,
      "grad_norm": 0.2370804399251938,
      "learning_rate": 2.5633640731412412e-05,
      "loss": 0.1564,
      "step": 74
    },
    {
      "epoch": 0.08431999437866704,
      "grad_norm": 0.38529258966445923,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 0.2007,
      "step": 75
    },
    {
      "epoch": 0.08431999437866704,
      "eval_loss": 0.13140296936035156,
      "eval_runtime": 1.1131,
      "eval_samples_per_second": 44.918,
      "eval_steps_per_second": 11.679,
      "step": 75
    },
    {
      "epoch": 0.0854442609703826,
      "grad_norm": 0.0939943939447403,
      "learning_rate": 2.3444344707738015e-05,
      "loss": 0.1148,
      "step": 76
    },
    {
      "epoch": 0.08656852756209817,
      "grad_norm": 0.11299529671669006,
      "learning_rate": 2.2400865784401e-05,
      "loss": 0.1161,
      "step": 77
    },
    {
      "epoch": 0.08769279415381372,
      "grad_norm": 0.15029741823673248,
      "learning_rate": 2.1393033535713093e-05,
      "loss": 0.1721,
      "step": 78
    },
    {
      "epoch": 0.08881706074552928,
      "grad_norm": 0.13788387179374695,
      "learning_rate": 2.0421950011441354e-05,
      "loss": 0.1297,
      "step": 79
    },
    {
      "epoch": 0.08994132733724484,
      "grad_norm": 0.1600455492734909,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 0.1631,
      "step": 80
    },
    {
      "epoch": 0.09106559392896041,
      "grad_norm": 0.18141554296016693,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 0.1658,
      "step": 81
    },
    {
      "epoch": 0.09218986052067596,
      "grad_norm": 0.17319364845752716,
      "learning_rate": 1.77396025983391e-05,
      "loss": 0.1626,
      "step": 82
    },
    {
      "epoch": 0.09331412711239152,
      "grad_norm": 0.16933465003967285,
      "learning_rate": 1.6925713641057904e-05,
      "loss": 0.1434,
      "step": 83
    },
    {
      "epoch": 0.09443839370410709,
      "grad_norm": 0.18129543960094452,
      "learning_rate": 1.6153458356909176e-05,
      "loss": 0.1479,
      "step": 84
    },
    {
      "epoch": 0.09556266029582265,
      "grad_norm": 0.19726185500621796,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 0.1469,
      "step": 85
    },
    {
      "epoch": 0.0966869268875382,
      "grad_norm": 0.21088498830795288,
      "learning_rate": 1.4737180158065644e-05,
      "loss": 0.1468,
      "step": 86
    },
    {
      "epoch": 0.09781119347925377,
      "grad_norm": 0.2601269781589508,
      "learning_rate": 1.4094705922787687e-05,
      "loss": 0.1458,
      "step": 87
    },
    {
      "epoch": 0.09893546007096933,
      "grad_norm": 0.12659643590450287,
      "learning_rate": 1.3496961026017687e-05,
      "loss": 0.1169,
      "step": 88
    },
    {
      "epoch": 0.1000597266626849,
      "grad_norm": 0.11825371533632278,
      "learning_rate": 1.2944599093024267e-05,
      "loss": 0.1294,
      "step": 89
    },
    {
      "epoch": 0.10118399325440045,
      "grad_norm": 0.1318565011024475,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 0.1393,
      "step": 90
    },
    {
      "epoch": 0.10230825984611601,
      "grad_norm": 0.13765253126621246,
      "learning_rate": 1.1978389830953907e-05,
      "loss": 0.1491,
      "step": 91
    },
    {
      "epoch": 0.10343252643783157,
      "grad_norm": 0.14009222388267517,
      "learning_rate": 1.1565599037519316e-05,
      "loss": 0.1435,
      "step": 92
    },
    {
      "epoch": 0.10455679302954714,
      "grad_norm": 0.147396519780159,
      "learning_rate": 1.1200303123839742e-05,
      "loss": 0.1487,
      "step": 93
    },
    {
      "epoch": 0.10568105962126269,
      "grad_norm": 0.1817561388015747,
      "learning_rate": 1.088290153563358e-05,
      "loss": 0.1747,
      "step": 94
    },
    {
      "epoch": 0.10680532621297825,
      "grad_norm": 0.1505913883447647,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 0.1246,
      "step": 95
    },
    {
      "epoch": 0.10792959280469382,
      "grad_norm": 0.19003218412399292,
      "learning_rate": 1.0393116880286118e-05,
      "loss": 0.1556,
      "step": 96
    },
    {
      "epoch": 0.10905385939640937,
      "grad_norm": 0.21154335141181946,
      "learning_rate": 1.0221269385474488e-05,
      "loss": 0.1642,
      "step": 97
    },
    {
      "epoch": 0.11017812598812493,
      "grad_norm": 0.20406153798103333,
      "learning_rate": 1.0098386775155147e-05,
      "loss": 0.143,
      "step": 98
    },
    {
      "epoch": 0.1113023925798405,
      "grad_norm": 0.24525730311870575,
      "learning_rate": 1.0024603419658329e-05,
      "loss": 0.1574,
      "step": 99
    },
    {
      "epoch": 0.11242665917155606,
      "grad_norm": 0.3504658043384552,
      "learning_rate": 1e-05,
      "loss": 0.2159,
      "step": 100
    },
    {
      "epoch": 0.11242665917155606,
      "eval_loss": 0.12831655144691467,
      "eval_runtime": 1.1133,
      "eval_samples_per_second": 44.913,
      "eval_steps_per_second": 11.677,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 3.24961789018112e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}