{
  "best_metric": 0.13168495893478394,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.081799591002045,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008179959100204499,
      "grad_norm": 0.9785810112953186,
      "learning_rate": 1e-05,
      "loss": 0.3676,
      "step": 1
    },
    {
      "epoch": 0.0008179959100204499,
      "eval_loss": 0.6463504433631897,
      "eval_runtime": 159.0078,
      "eval_samples_per_second": 12.949,
      "eval_steps_per_second": 1.623,
      "step": 1
    },
    {
      "epoch": 0.0016359918200408998,
      "grad_norm": 1.1243798732757568,
      "learning_rate": 2e-05,
      "loss": 0.3877,
      "step": 2
    },
    {
      "epoch": 0.00245398773006135,
      "grad_norm": 0.9974974393844604,
      "learning_rate": 3e-05,
      "loss": 0.379,
      "step": 3
    },
    {
      "epoch": 0.0032719836400817996,
      "grad_norm": 0.8009510040283203,
      "learning_rate": 4e-05,
      "loss": 0.3552,
      "step": 4
    },
    {
      "epoch": 0.00408997955010225,
      "grad_norm": 0.6887012124061584,
      "learning_rate": 5e-05,
      "loss": 0.2944,
      "step": 5
    },
    {
      "epoch": 0.0049079754601227,
      "grad_norm": 0.6000428199768066,
      "learning_rate": 6e-05,
      "loss": 0.2534,
      "step": 6
    },
    {
      "epoch": 0.0057259713701431495,
      "grad_norm": 0.6452663540840149,
      "learning_rate": 7e-05,
      "loss": 0.2077,
      "step": 7
    },
    {
      "epoch": 0.006543967280163599,
      "grad_norm": 0.4751436412334442,
      "learning_rate": 8e-05,
      "loss": 0.1534,
      "step": 8
    },
    {
      "epoch": 0.007361963190184049,
      "grad_norm": 0.37796375155448914,
      "learning_rate": 9e-05,
      "loss": 0.1327,
      "step": 9
    },
    {
      "epoch": 0.0081799591002045,
      "grad_norm": 0.8398392200469971,
      "learning_rate": 0.0001,
      "loss": 0.1406,
      "step": 10
    },
    {
      "epoch": 0.00899795501022495,
      "grad_norm": 0.23226913809776306,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.13,
      "step": 11
    },
    {
      "epoch": 0.0098159509202454,
      "grad_norm": 0.19458428025245667,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.1257,
      "step": 12
    },
    {
      "epoch": 0.01063394683026585,
      "grad_norm": 0.1287323385477066,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.1212,
      "step": 13
    },
    {
      "epoch": 0.011451942740286299,
      "grad_norm": 0.09111806750297546,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.1194,
      "step": 14
    },
    {
      "epoch": 0.012269938650306749,
      "grad_norm": 0.30057820677757263,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.1197,
      "step": 15
    },
    {
      "epoch": 0.013087934560327199,
      "grad_norm": 0.05541268363595009,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1178,
      "step": 16
    },
    {
      "epoch": 0.013905930470347648,
      "grad_norm": 0.2968832850456238,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.1187,
      "step": 17
    },
    {
      "epoch": 0.014723926380368098,
      "grad_norm": 0.053920552134513855,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.115,
      "step": 18
    },
    {
      "epoch": 0.015541922290388548,
      "grad_norm": 0.031204992905259132,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1158,
      "step": 19
    },
    {
      "epoch": 0.016359918200409,
      "grad_norm": 0.03834879770874977,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1136,
      "step": 20
    },
    {
      "epoch": 0.01717791411042945,
      "grad_norm": 0.06296058744192123,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.115,
      "step": 21
    },
    {
      "epoch": 0.0179959100204499,
      "grad_norm": 0.23524504899978638,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1154,
      "step": 22
    },
    {
      "epoch": 0.01881390593047035,
      "grad_norm": 7.033353805541992,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1245,
      "step": 23
    },
    {
      "epoch": 0.0196319018404908,
      "grad_norm": 0.3365825414657593,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.1222,
      "step": 24
    },
    {
      "epoch": 0.02044989775051125,
      "grad_norm": 0.013476976193487644,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1155,
      "step": 25
    },
    {
      "epoch": 0.0212678936605317,
      "grad_norm": 0.013657408766448498,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.1171,
      "step": 26
    },
    {
      "epoch": 0.022085889570552148,
      "grad_norm": 0.016086701303720474,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.1188,
      "step": 27
    },
    {
      "epoch": 0.022903885480572598,
      "grad_norm": 0.014190609566867352,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1201,
      "step": 28
    },
    {
      "epoch": 0.023721881390593048,
      "grad_norm": 0.015120434574782848,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.1278,
      "step": 29
    },
    {
      "epoch": 0.024539877300613498,
      "grad_norm": 0.11933290213346481,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1345,
      "step": 30
    },
    {
      "epoch": 0.025357873210633947,
      "grad_norm": 0.03551671281456947,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.1508,
      "step": 31
    },
    {
      "epoch": 0.026175869120654397,
      "grad_norm": 0.03801102936267853,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.1513,
      "step": 32
    },
    {
      "epoch": 0.026993865030674847,
      "grad_norm": 0.01589568518102169,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.1526,
      "step": 33
    },
    {
      "epoch": 0.027811860940695297,
      "grad_norm": 0.010979746468365192,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1585,
      "step": 34
    },
    {
      "epoch": 0.028629856850715747,
      "grad_norm": 0.01078648492693901,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1606,
      "step": 35
    },
    {
      "epoch": 0.029447852760736196,
      "grad_norm": 0.011973066255450249,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1618,
      "step": 36
    },
    {
      "epoch": 0.030265848670756646,
      "grad_norm": 0.017717402428388596,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1658,
      "step": 37
    },
    {
      "epoch": 0.031083844580777096,
      "grad_norm": 0.009199744090437889,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.1658,
      "step": 38
    },
    {
      "epoch": 0.03190184049079755,
      "grad_norm": 0.2190573662519455,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.1676,
      "step": 39
    },
    {
      "epoch": 0.032719836400818,
      "grad_norm": 0.010531465522944927,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1686,
      "step": 40
    },
    {
      "epoch": 0.03353783231083845,
      "grad_norm": 0.1139778196811676,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.1697,
      "step": 41
    },
    {
      "epoch": 0.0343558282208589,
      "grad_norm": 0.007362987846136093,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.1736,
      "step": 42
    },
    {
      "epoch": 0.03517382413087935,
      "grad_norm": 0.0163573045283556,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.1782,
      "step": 43
    },
    {
      "epoch": 0.0359918200408998,
      "grad_norm": 0.7911167144775391,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.181,
      "step": 44
    },
    {
      "epoch": 0.03680981595092025,
      "grad_norm": 0.007592629175633192,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1844,
      "step": 45
    },
    {
      "epoch": 0.0376278118609407,
      "grad_norm": 0.035700421780347824,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1929,
      "step": 46
    },
    {
      "epoch": 0.03844580777096115,
      "grad_norm": 0.018869740888476372,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.206,
      "step": 47
    },
    {
      "epoch": 0.0392638036809816,
      "grad_norm": 0.008273100480437279,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.2157,
      "step": 48
    },
    {
      "epoch": 0.04008179959100205,
      "grad_norm": 0.008044171147048473,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.2195,
      "step": 49
    },
    {
      "epoch": 0.0408997955010225,
      "grad_norm": 0.010464195162057877,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2338,
      "step": 50
    },
    {
      "epoch": 0.0408997955010225,
      "eval_loss": 0.13240806758403778,
      "eval_runtime": 160.7846,
      "eval_samples_per_second": 12.806,
      "eval_steps_per_second": 1.605,
      "step": 50
    },
    {
      "epoch": 0.04171779141104295,
      "grad_norm": 0.011765269562602043,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0758,
      "step": 51
    },
    {
      "epoch": 0.0425357873210634,
      "grad_norm": 0.08227711915969849,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0783,
      "step": 52
    },
    {
      "epoch": 0.043353783231083846,
      "grad_norm": 0.0031160374637693167,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0788,
      "step": 53
    },
    {
      "epoch": 0.044171779141104296,
      "grad_norm": 0.011308848857879639,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0795,
      "step": 54
    },
    {
      "epoch": 0.044989775051124746,
      "grad_norm": 0.13721175491809845,
      "learning_rate": 5e-05,
      "loss": 0.0819,
      "step": 55
    },
    {
      "epoch": 0.045807770961145196,
      "grad_norm": 0.006852192338556051,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.082,
      "step": 56
    },
    {
      "epoch": 0.046625766871165646,
      "grad_norm": 0.29579928517341614,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.083,
      "step": 57
    },
    {
      "epoch": 0.047443762781186095,
      "grad_norm": 0.007515231147408485,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0834,
      "step": 58
    },
    {
      "epoch": 0.048261758691206545,
      "grad_norm": 0.004428052809089422,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0852,
      "step": 59
    },
    {
      "epoch": 0.049079754601226995,
      "grad_norm": 0.8864473104476929,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0947,
      "step": 60
    },
    {
      "epoch": 0.049897750511247445,
      "grad_norm": 0.05357252061367035,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0993,
      "step": 61
    },
    {
      "epoch": 0.050715746421267895,
      "grad_norm": 1.1230288743972778,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.1072,
      "step": 62
    },
    {
      "epoch": 0.051533742331288344,
      "grad_norm": 0.11107894033193588,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.1049,
      "step": 63
    },
    {
      "epoch": 0.052351738241308794,
      "grad_norm": 0.0049737924709916115,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1022,
      "step": 64
    },
    {
      "epoch": 0.053169734151329244,
      "grad_norm": 0.0029193395748734474,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1035,
      "step": 65
    },
    {
      "epoch": 0.053987730061349694,
      "grad_norm": 0.011156219989061356,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1053,
      "step": 66
    },
    {
      "epoch": 0.054805725971370144,
      "grad_norm": 0.003020926844328642,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.1056,
      "step": 67
    },
    {
      "epoch": 0.05562372188139059,
      "grad_norm": 0.01634683832526207,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1065,
      "step": 68
    },
    {
      "epoch": 0.05644171779141104,
      "grad_norm": 0.006313734222203493,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1064,
      "step": 69
    },
    {
      "epoch": 0.05725971370143149,
      "grad_norm": 0.005186033435165882,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1072,
      "step": 70
    },
    {
      "epoch": 0.05807770961145194,
      "grad_norm": 0.04070008173584938,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.1088,
      "step": 71
    },
    {
      "epoch": 0.05889570552147239,
      "grad_norm": 0.01637279987335205,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.1092,
      "step": 72
    },
    {
      "epoch": 0.05971370143149284,
      "grad_norm": 0.17546702921390533,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1141,
      "step": 73
    },
    {
      "epoch": 0.06053169734151329,
      "grad_norm": 0.12339083105325699,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.1127,
      "step": 74
    },
    {
      "epoch": 0.06134969325153374,
      "grad_norm": 0.005719954613596201,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.112,
      "step": 75
    },
    {
      "epoch": 0.06216768916155419,
      "grad_norm": 0.005668998695909977,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1128,
      "step": 76
    },
    {
      "epoch": 0.06298568507157465,
      "grad_norm": 0.007494923193007708,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.1139,
      "step": 77
    },
    {
      "epoch": 0.0638036809815951,
      "grad_norm": 0.9686630368232727,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1185,
      "step": 78
    },
    {
      "epoch": 0.06462167689161555,
      "grad_norm": 0.005378738045692444,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1269,
      "step": 79
    },
    {
      "epoch": 0.065439672801636,
      "grad_norm": 0.008375857956707478,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1394,
      "step": 80
    },
    {
      "epoch": 0.06625766871165645,
      "grad_norm": 0.0262595321983099,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.1466,
      "step": 81
    },
    {
      "epoch": 0.0670756646216769,
      "grad_norm": 0.004784999880939722,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1518,
      "step": 82
    },
    {
      "epoch": 0.06789366053169735,
      "grad_norm": 0.541429877281189,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.158,
      "step": 83
    },
    {
      "epoch": 0.0687116564417178,
      "grad_norm": 0.17787200212478638,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1617,
      "step": 84
    },
    {
      "epoch": 0.06952965235173825,
      "grad_norm": 0.7806742787361145,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1635,
      "step": 85
    },
    {
      "epoch": 0.0703476482617587,
      "grad_norm": 0.004796426277607679,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.1595,
      "step": 86
    },
    {
      "epoch": 0.07116564417177915,
      "grad_norm": 1.1767271757125854,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1716,
      "step": 87
    },
    {
      "epoch": 0.0719836400817996,
      "grad_norm": 0.8248836994171143,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1651,
      "step": 88
    },
    {
      "epoch": 0.07280163599182005,
      "grad_norm": 0.005601507145911455,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.165,
      "step": 89
    },
    {
      "epoch": 0.0736196319018405,
      "grad_norm": 0.20898360013961792,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.1697,
      "step": 90
    },
    {
      "epoch": 0.07443762781186095,
      "grad_norm": 0.00812277290970087,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1666,
      "step": 91
    },
    {
      "epoch": 0.0752556237218814,
      "grad_norm": 0.005786346737295389,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1707,
      "step": 92
    },
    {
      "epoch": 0.07607361963190185,
      "grad_norm": 0.004848749376833439,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1748,
      "step": 93
    },
    {
      "epoch": 0.0768916155419223,
      "grad_norm": 0.7034335732460022,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1838,
      "step": 94
    },
    {
      "epoch": 0.07770961145194274,
      "grad_norm": 0.721812903881073,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.202,
      "step": 95
    },
    {
      "epoch": 0.0785276073619632,
      "grad_norm": 0.6704414486885071,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2159,
      "step": 96
    },
    {
      "epoch": 0.07934560327198364,
      "grad_norm": 1.4202635288238525,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.2141,
      "step": 97
    },
    {
      "epoch": 0.0801635991820041,
      "grad_norm": 0.36247241497039795,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.2182,
      "step": 98
    },
    {
      "epoch": 0.08098159509202454,
      "grad_norm": 0.008243364281952381,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.2288,
      "step": 99
    },
    {
      "epoch": 0.081799591002045,
      "grad_norm": 1.1368809938430786,
      "learning_rate": 0.0,
      "loss": 0.2542,
      "step": 100
    },
    {
      "epoch": 0.081799591002045,
      "eval_loss": 0.13168495893478394,
      "eval_runtime": 160.7443,
      "eval_samples_per_second": 12.809,
      "eval_steps_per_second": 1.605,
      "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": 1.508513578745856e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}