{
  "best_metric": 1.325927972793579,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.006487503446486206,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.487503446486205e-05,
      "grad_norm": 0.65945965051651,
      "learning_rate": 1e-05,
      "loss": 0.837,
      "step": 1
    },
    {
      "epoch": 6.487503446486205e-05,
      "eval_loss": 1.8628575801849365,
      "eval_runtime": 1747.9989,
      "eval_samples_per_second": 7.426,
      "eval_steps_per_second": 1.857,
      "step": 1
    },
    {
      "epoch": 0.0001297500689297241,
      "grad_norm": 0.7506418824195862,
      "learning_rate": 2e-05,
      "loss": 1.2912,
      "step": 2
    },
    {
      "epoch": 0.0001946251033945862,
      "grad_norm": 0.6613309383392334,
      "learning_rate": 3e-05,
      "loss": 0.7751,
      "step": 3
    },
    {
      "epoch": 0.0002595001378594482,
      "grad_norm": 0.7034075856208801,
      "learning_rate": 4e-05,
      "loss": 0.9947,
      "step": 4
    },
    {
      "epoch": 0.0003243751723243103,
      "grad_norm": 0.8446619510650635,
      "learning_rate": 5e-05,
      "loss": 1.063,
      "step": 5
    },
    {
      "epoch": 0.0003892502067891724,
      "grad_norm": 0.8111912608146667,
      "learning_rate": 6e-05,
      "loss": 0.9536,
      "step": 6
    },
    {
      "epoch": 0.00045412524125403443,
      "grad_norm": 0.6236023306846619,
      "learning_rate": 7e-05,
      "loss": 1.0558,
      "step": 7
    },
    {
      "epoch": 0.0005190002757188964,
      "grad_norm": 0.6202384233474731,
      "learning_rate": 8e-05,
      "loss": 1.2574,
      "step": 8
    },
    {
      "epoch": 0.0005838753101837585,
      "grad_norm": 0.46054795384407043,
      "learning_rate": 9e-05,
      "loss": 0.9441,
      "step": 9
    },
    {
      "epoch": 0.0006487503446486206,
      "grad_norm": 0.41842198371887207,
      "learning_rate": 0.0001,
      "loss": 1.0572,
      "step": 10
    },
    {
      "epoch": 0.0007136253791134826,
      "grad_norm": 0.43228819966316223,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.9306,
      "step": 11
    },
    {
      "epoch": 0.0007785004135783448,
      "grad_norm": 0.5606890916824341,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.3437,
      "step": 12
    },
    {
      "epoch": 0.0008433754480432068,
      "grad_norm": 0.6623042821884155,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.2851,
      "step": 13
    },
    {
      "epoch": 0.0009082504825080689,
      "grad_norm": 0.5418866872787476,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.2339,
      "step": 14
    },
    {
      "epoch": 0.0009731255169729309,
      "grad_norm": 0.5721413493156433,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.085,
      "step": 15
    },
    {
      "epoch": 0.0010380005514377929,
      "grad_norm": 0.4557238221168518,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.3243,
      "step": 16
    },
    {
      "epoch": 0.001102875585902655,
      "grad_norm": 0.3978056311607361,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.9198,
      "step": 17
    },
    {
      "epoch": 0.001167750620367517,
      "grad_norm": 0.4164397418498993,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.9494,
      "step": 18
    },
    {
      "epoch": 0.001232625654832379,
      "grad_norm": 0.38695651292800903,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2792,
      "step": 19
    },
    {
      "epoch": 0.0012975006892972413,
      "grad_norm": 0.400411993265152,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.9653,
      "step": 20
    },
    {
      "epoch": 0.0013623757237621033,
      "grad_norm": 0.432561993598938,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.1407,
      "step": 21
    },
    {
      "epoch": 0.0014272507582269653,
      "grad_norm": 0.45154693722724915,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.2837,
      "step": 22
    },
    {
      "epoch": 0.0014921257926918273,
      "grad_norm": 0.5273919701576233,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.6754,
      "step": 23
    },
    {
      "epoch": 0.0015570008271566895,
      "grad_norm": 0.45300814509391785,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.1316,
      "step": 24
    },
    {
      "epoch": 0.0016218758616215515,
      "grad_norm": 0.5035930871963501,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.2941,
      "step": 25
    },
    {
      "epoch": 0.0016867508960864135,
      "grad_norm": 0.48046597838401794,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.0482,
      "step": 26
    },
    {
      "epoch": 0.0017516259305512755,
      "grad_norm": 0.5023167729377747,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.1976,
      "step": 27
    },
    {
      "epoch": 0.0018165009650161377,
      "grad_norm": 0.4501717686653137,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.055,
      "step": 28
    },
    {
      "epoch": 0.0018813759994809997,
      "grad_norm": 0.5412274599075317,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.497,
      "step": 29
    },
    {
      "epoch": 0.0019462510339458617,
      "grad_norm": 0.522600531578064,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.6231,
      "step": 30
    },
    {
      "epoch": 0.002011126068410724,
      "grad_norm": 0.505004346370697,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.1963,
      "step": 31
    },
    {
      "epoch": 0.0020760011028755857,
      "grad_norm": 0.571204662322998,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.6778,
      "step": 32
    },
    {
      "epoch": 0.002140876137340448,
      "grad_norm": 0.6349219679832458,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.508,
      "step": 33
    },
    {
      "epoch": 0.00220575117180531,
      "grad_norm": 0.5966265201568604,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.6876,
      "step": 34
    },
    {
      "epoch": 0.002270626206270172,
      "grad_norm": 0.5677382946014404,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.4076,
      "step": 35
    },
    {
      "epoch": 0.002335501240735034,
      "grad_norm": 0.6977220177650452,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.7096,
      "step": 36
    },
    {
      "epoch": 0.0024003762751998964,
      "grad_norm": 0.697718620300293,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.0765,
      "step": 37
    },
    {
      "epoch": 0.002465251309664758,
      "grad_norm": 0.7941728830337524,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.503,
      "step": 38
    },
    {
      "epoch": 0.0025301263441296204,
      "grad_norm": 0.682919979095459,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.7776,
      "step": 39
    },
    {
      "epoch": 0.0025950013785944826,
      "grad_norm": 0.7911466360092163,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0306,
      "step": 40
    },
    {
      "epoch": 0.0026598764130593444,
      "grad_norm": 0.7650830149650574,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.9594,
      "step": 41
    },
    {
      "epoch": 0.0027247514475242066,
      "grad_norm": 0.8082930445671082,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.8103,
      "step": 42
    },
    {
      "epoch": 0.0027896264819890684,
      "grad_norm": 0.934689462184906,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.7029,
      "step": 43
    },
    {
      "epoch": 0.0028545015164539306,
      "grad_norm": 1.1539926528930664,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.6738,
      "step": 44
    },
    {
      "epoch": 0.002919376550918793,
      "grad_norm": 1.2392182350158691,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.1153,
      "step": 45
    },
    {
      "epoch": 0.0029842515853836546,
      "grad_norm": 1.680818796157837,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7247,
      "step": 46
    },
    {
      "epoch": 0.003049126619848517,
      "grad_norm": 1.8292930126190186,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.0977,
      "step": 47
    },
    {
      "epoch": 0.003114001654313379,
      "grad_norm": 2.9237239360809326,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.8703,
      "step": 48
    },
    {
      "epoch": 0.003178876688778241,
      "grad_norm": 2.1567187309265137,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.8881,
      "step": 49
    },
    {
      "epoch": 0.003243751723243103,
      "grad_norm": 3.8776872158050537,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.3531,
      "step": 50
    },
    {
      "epoch": 0.003243751723243103,
      "eval_loss": 1.363798975944519,
      "eval_runtime": 1752.2468,
      "eval_samples_per_second": 7.408,
      "eval_steps_per_second": 1.852,
      "step": 50
    },
    {
      "epoch": 0.0033086267577079652,
      "grad_norm": 0.4849475920200348,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.8282,
      "step": 51
    },
    {
      "epoch": 0.003373501792172827,
      "grad_norm": 0.37002480030059814,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.7841,
      "step": 52
    },
    {
      "epoch": 0.0034383768266376892,
      "grad_norm": 0.4096565544605255,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.7244,
      "step": 53
    },
    {
      "epoch": 0.003503251861102551,
      "grad_norm": 0.4696180820465088,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.1759,
      "step": 54
    },
    {
      "epoch": 0.0035681268955674132,
      "grad_norm": 0.43438711762428284,
      "learning_rate": 5e-05,
      "loss": 0.9274,
      "step": 55
    },
    {
      "epoch": 0.0036330019300322754,
      "grad_norm": 0.41294389963150024,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.8646,
      "step": 56
    },
    {
      "epoch": 0.0036978769644971372,
      "grad_norm": 0.36452946066856384,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.9131,
      "step": 57
    },
    {
      "epoch": 0.0037627519989619994,
      "grad_norm": 0.3747154772281647,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.9117,
      "step": 58
    },
    {
      "epoch": 0.0038276270334268617,
      "grad_norm": 0.40438297390937805,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.2761,
      "step": 59
    },
    {
      "epoch": 0.0038925020678917234,
      "grad_norm": 0.352256715297699,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.0757,
      "step": 60
    },
    {
      "epoch": 0.003957377102356586,
      "grad_norm": 0.34723353385925293,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.8732,
      "step": 61
    },
    {
      "epoch": 0.004022252136821448,
      "grad_norm": 0.37071236968040466,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.9158,
      "step": 62
    },
    {
      "epoch": 0.00408712717128631,
      "grad_norm": 0.38852158188819885,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.8826,
      "step": 63
    },
    {
      "epoch": 0.004152002205751171,
      "grad_norm": 0.360282838344574,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8892,
      "step": 64
    },
    {
      "epoch": 0.004216877240216034,
      "grad_norm": 0.38755518198013306,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.1074,
      "step": 65
    },
    {
      "epoch": 0.004281752274680896,
      "grad_norm": 0.39956825971603394,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.0231,
      "step": 66
    },
    {
      "epoch": 0.004346627309145758,
      "grad_norm": 0.401048868894577,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.1309,
      "step": 67
    },
    {
      "epoch": 0.00441150234361062,
      "grad_norm": 0.39506635069847107,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.1455,
      "step": 68
    },
    {
      "epoch": 0.0044763773780754825,
      "grad_norm": 0.3784264028072357,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.8688,
      "step": 69
    },
    {
      "epoch": 0.004541252412540344,
      "grad_norm": 0.4321235120296478,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8886,
      "step": 70
    },
    {
      "epoch": 0.004606127447005206,
      "grad_norm": 0.4353868067264557,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.2471,
      "step": 71
    },
    {
      "epoch": 0.004671002481470068,
      "grad_norm": 0.44864824414253235,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.0473,
      "step": 72
    },
    {
      "epoch": 0.0047358775159349305,
      "grad_norm": 0.46487781405448914,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9981,
      "step": 73
    },
    {
      "epoch": 0.004800752550399793,
      "grad_norm": 0.4789814352989197,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.9889,
      "step": 74
    },
    {
      "epoch": 0.004865627584864654,
      "grad_norm": 0.46205461025238037,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.0581,
      "step": 75
    },
    {
      "epoch": 0.004930502619329516,
      "grad_norm": 0.4730319380760193,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.9925,
      "step": 76
    },
    {
      "epoch": 0.0049953776537943785,
      "grad_norm": 0.47287988662719727,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.2184,
      "step": 77
    },
    {
      "epoch": 0.005060252688259241,
      "grad_norm": 0.5465039610862732,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.4309,
      "step": 78
    },
    {
      "epoch": 0.005125127722724103,
      "grad_norm": 0.5158198475837708,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.446,
      "step": 79
    },
    {
      "epoch": 0.005190002757188965,
      "grad_norm": 0.5407456755638123,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.1469,
      "step": 80
    },
    {
      "epoch": 0.0052548777916538265,
      "grad_norm": 0.606384813785553,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.6318,
      "step": 81
    },
    {
      "epoch": 0.005319752826118689,
      "grad_norm": 0.5945765972137451,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.4171,
      "step": 82
    },
    {
      "epoch": 0.005384627860583551,
      "grad_norm": 0.5641322135925293,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.6514,
      "step": 83
    },
    {
      "epoch": 0.005449502895048413,
      "grad_norm": 0.7056270241737366,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.4912,
      "step": 84
    },
    {
      "epoch": 0.005514377929513275,
      "grad_norm": 0.6317409873008728,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.0169,
      "step": 85
    },
    {
      "epoch": 0.005579252963978137,
      "grad_norm": 0.7745837569236755,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.9579,
      "step": 86
    },
    {
      "epoch": 0.005644127998442999,
      "grad_norm": 0.7412452101707458,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.8417,
      "step": 87
    },
    {
      "epoch": 0.005709003032907861,
      "grad_norm": 0.6834709644317627,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.5746,
      "step": 88
    },
    {
      "epoch": 0.005773878067372723,
      "grad_norm": 0.7952920198440552,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.6825,
      "step": 89
    },
    {
      "epoch": 0.005838753101837586,
      "grad_norm": 0.6980010271072388,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.8503,
      "step": 90
    },
    {
      "epoch": 0.005903628136302448,
      "grad_norm": 0.842880129814148,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.8676,
      "step": 91
    },
    {
      "epoch": 0.005968503170767309,
      "grad_norm": 0.8270924091339111,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.8416,
      "step": 92
    },
    {
      "epoch": 0.006033378205232171,
      "grad_norm": 0.877210795879364,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.8189,
      "step": 93
    },
    {
      "epoch": 0.006098253239697034,
      "grad_norm": 0.9402266144752502,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.5157,
      "step": 94
    },
    {
      "epoch": 0.006163128274161896,
      "grad_norm": 1.0260732173919678,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.6211,
      "step": 95
    },
    {
      "epoch": 0.006228003308626758,
      "grad_norm": 1.1405702829360962,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.8139,
      "step": 96
    },
    {
      "epoch": 0.006292878343091619,
      "grad_norm": 1.3093563318252563,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.876,
      "step": 97
    },
    {
      "epoch": 0.006357753377556482,
      "grad_norm": 1.6507575511932373,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.8827,
      "step": 98
    },
    {
      "epoch": 0.006422628412021344,
      "grad_norm": 2.4827072620391846,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.0387,
      "step": 99
    },
    {
      "epoch": 0.006487503446486206,
      "grad_norm": 2.8122284412384033,
      "learning_rate": 0.0,
      "loss": 1.9601,
      "step": 100
    },
    {
      "epoch": 0.006487503446486206,
      "eval_loss": 1.325927972793579,
      "eval_runtime": 1752.2492,
      "eval_samples_per_second": 7.408,
      "eval_steps_per_second": 1.852,
      "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": 8.503799496415642e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}