{
  "best_metric": 0.3503866195678711,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.0020115563914689895,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0115563914689893e-05,
      "grad_norm": 0.3044566512107849,
      "learning_rate": 4e-05,
      "loss": 0.4435,
      "step": 1
    },
    {
      "epoch": 2.0115563914689893e-05,
      "eval_loss": 1.1716877222061157,
      "eval_runtime": 5944.9564,
      "eval_samples_per_second": 3.521,
      "eval_steps_per_second": 1.76,
      "step": 1
    },
    {
      "epoch": 4.023112782937979e-05,
      "grad_norm": 0.5846538543701172,
      "learning_rate": 8e-05,
      "loss": 0.3692,
      "step": 2
    },
    {
      "epoch": 6.034669174406968e-05,
      "grad_norm": 0.6687699556350708,
      "learning_rate": 0.00012,
      "loss": 0.4194,
      "step": 3
    },
    {
      "epoch": 8.046225565875957e-05,
      "grad_norm": 1.0227057933807373,
      "learning_rate": 0.00016,
      "loss": 0.5194,
      "step": 4
    },
    {
      "epoch": 0.00010057781957344947,
      "grad_norm": 0.7381047606468201,
      "learning_rate": 0.0002,
      "loss": 0.4124,
      "step": 5
    },
    {
      "epoch": 0.00012069338348813936,
      "grad_norm": 0.8244189620018005,
      "learning_rate": 0.00019994532573409262,
      "loss": 0.5341,
      "step": 6
    },
    {
      "epoch": 0.00014080894740282925,
      "grad_norm": 0.8337830305099487,
      "learning_rate": 0.00019978136272187747,
      "loss": 0.1842,
      "step": 7
    },
    {
      "epoch": 0.00016092451131751915,
      "grad_norm": 0.7174459099769592,
      "learning_rate": 0.00019950829025450114,
      "loss": 0.1288,
      "step": 8
    },
    {
      "epoch": 0.00018104007523220904,
      "grad_norm": 0.7341412901878357,
      "learning_rate": 0.00019912640693269752,
      "loss": 0.16,
      "step": 9
    },
    {
      "epoch": 0.00020115563914689893,
      "grad_norm": 1.1397154331207275,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.3549,
      "step": 10
    },
    {
      "epoch": 0.00022127120306158883,
      "grad_norm": 0.7693608999252319,
      "learning_rate": 0.00019803799658748094,
      "loss": 0.2105,
      "step": 11
    },
    {
      "epoch": 0.00024138676697627872,
      "grad_norm": 2.2909274101257324,
      "learning_rate": 0.0001973326597248006,
      "loss": 0.4326,
      "step": 12
    },
    {
      "epoch": 0.00026150233089096864,
      "grad_norm": 0.8318089246749878,
      "learning_rate": 0.00019652089102773488,
      "loss": 0.2368,
      "step": 13
    },
    {
      "epoch": 0.0002816178948056585,
      "grad_norm": 1.456488013267517,
      "learning_rate": 0.00019560357815343577,
      "loss": 0.4398,
      "step": 14
    },
    {
      "epoch": 0.00030173345872034843,
      "grad_norm": 0.5268795490264893,
      "learning_rate": 0.00019458172417006347,
      "loss": 0.145,
      "step": 15
    },
    {
      "epoch": 0.0003218490226350383,
      "grad_norm": 0.5436660647392273,
      "learning_rate": 0.0001934564464599461,
      "loss": 0.1519,
      "step": 16
    },
    {
      "epoch": 0.0003419645865497282,
      "grad_norm": 0.7317480444908142,
      "learning_rate": 0.00019222897549773848,
      "loss": 0.1956,
      "step": 17
    },
    {
      "epoch": 0.0003620801504644181,
      "grad_norm": 1.3020880222320557,
      "learning_rate": 0.00019090065350491626,
      "loss": 0.3463,
      "step": 18
    },
    {
      "epoch": 0.000382195714379108,
      "grad_norm": 1.1081501245498657,
      "learning_rate": 0.00018947293298207635,
      "loss": 0.2221,
      "step": 19
    },
    {
      "epoch": 0.00040231127829379787,
      "grad_norm": 1.220346450805664,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.2317,
      "step": 20
    },
    {
      "epoch": 0.0004224268422084878,
      "grad_norm": 1.145397663116455,
      "learning_rate": 0.00018632564809575742,
      "loss": 0.3508,
      "step": 21
    },
    {
      "epoch": 0.00044254240612317766,
      "grad_norm": 0.9851236939430237,
      "learning_rate": 0.00018460952524209355,
      "loss": 0.2323,
      "step": 22
    },
    {
      "epoch": 0.0004626579700378676,
      "grad_norm": 1.1991878747940063,
      "learning_rate": 0.00018280088311480201,
      "loss": 0.194,
      "step": 23
    },
    {
      "epoch": 0.00048277353395255744,
      "grad_norm": 1.258394718170166,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.3487,
      "step": 24
    },
    {
      "epoch": 0.0005028890978672474,
      "grad_norm": 1.0028445720672607,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.3282,
      "step": 25
    },
    {
      "epoch": 0.0005028890978672474,
      "eval_loss": 0.38313478231430054,
      "eval_runtime": 5968.8845,
      "eval_samples_per_second": 3.507,
      "eval_steps_per_second": 1.753,
      "step": 25
    },
    {
      "epoch": 0.0005230046617819373,
      "grad_norm": 1.2087231874465942,
      "learning_rate": 0.00017684011108568592,
      "loss": 0.3541,
      "step": 26
    },
    {
      "epoch": 0.0005431202256966271,
      "grad_norm": 0.7510756254196167,
      "learning_rate": 0.0001746821476984154,
      "loss": 0.2474,
      "step": 27
    },
    {
      "epoch": 0.000563235789611317,
      "grad_norm": 0.9615175127983093,
      "learning_rate": 0.00017244252047910892,
      "loss": 0.4285,
      "step": 28
    },
    {
      "epoch": 0.0005833513535260069,
      "grad_norm": 1.6521743535995483,
      "learning_rate": 0.00017012367842724887,
      "loss": 0.5122,
      "step": 29
    },
    {
      "epoch": 0.0006034669174406969,
      "grad_norm": 1.0975160598754883,
      "learning_rate": 0.00016772815716257412,
      "loss": 0.4345,
      "step": 30
    },
    {
      "epoch": 0.0006235824813553867,
      "grad_norm": 1.332993984222412,
      "learning_rate": 0.00016525857615241687,
      "loss": 0.1814,
      "step": 31
    },
    {
      "epoch": 0.0006436980452700766,
      "grad_norm": 2.3052821159362793,
      "learning_rate": 0.0001627176358473537,
      "loss": 0.764,
      "step": 32
    },
    {
      "epoch": 0.0006638136091847665,
      "grad_norm": 1.9049065113067627,
      "learning_rate": 0.00016010811472830252,
      "loss": 0.5676,
      "step": 33
    },
    {
      "epoch": 0.0006839291730994564,
      "grad_norm": 1.4157077074050903,
      "learning_rate": 0.00015743286626829437,
      "loss": 0.2885,
      "step": 34
    },
    {
      "epoch": 0.0007040447370141462,
      "grad_norm": 1.8599406480789185,
      "learning_rate": 0.00015469481581224272,
      "loss": 0.5417,
      "step": 35
    },
    {
      "epoch": 0.0007241603009288362,
      "grad_norm": 0.757952094078064,
      "learning_rate": 0.00015189695737812152,
      "loss": 0.2253,
      "step": 36
    },
    {
      "epoch": 0.0007442758648435261,
      "grad_norm": 1.1078306436538696,
      "learning_rate": 0.00014904235038305083,
      "loss": 0.1614,
      "step": 37
    },
    {
      "epoch": 0.000764391428758216,
      "grad_norm": 1.2288084030151367,
      "learning_rate": 0.0001461341162978688,
      "loss": 0.2767,
      "step": 38
    },
    {
      "epoch": 0.0007845069926729058,
      "grad_norm": 0.7424066066741943,
      "learning_rate": 0.00014317543523384928,
      "loss": 0.1715,
      "step": 39
    },
    {
      "epoch": 0.0008046225565875957,
      "grad_norm": 1.009460210800171,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.2123,
      "step": 40
    },
    {
      "epoch": 0.0008247381205022857,
      "grad_norm": 1.8544470071792603,
      "learning_rate": 0.00013711972489182208,
      "loss": 0.7898,
      "step": 41
    },
    {
      "epoch": 0.0008448536844169756,
      "grad_norm": 1.8500866889953613,
      "learning_rate": 0.00013402931744416433,
      "loss": 0.4095,
      "step": 42
    },
    {
      "epoch": 0.0008649692483316654,
      "grad_norm": 2.287600517272949,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6513,
      "step": 43
    },
    {
      "epoch": 0.0008850848122463553,
      "grad_norm": 0.6950022578239441,
      "learning_rate": 0.00012774029087618446,
      "loss": 0.098,
      "step": 44
    },
    {
      "epoch": 0.0009052003761610452,
      "grad_norm": 1.1519097089767456,
      "learning_rate": 0.00012454854871407994,
      "loss": 0.3887,
      "step": 45
    },
    {
      "epoch": 0.0009253159400757352,
      "grad_norm": 1.9645311832427979,
      "learning_rate": 0.0001213299630743747,
      "loss": 0.5686,
      "step": 46
    },
    {
      "epoch": 0.000945431503990425,
      "grad_norm": 2.0428481101989746,
      "learning_rate": 0.000118088053433211,
      "loss": 0.5198,
      "step": 47
    },
    {
      "epoch": 0.0009655470679051149,
      "grad_norm": 1.8423922061920166,
      "learning_rate": 0.0001148263647711842,
      "loss": 0.528,
      "step": 48
    },
    {
      "epoch": 0.0009856626318198048,
      "grad_norm": 3.1978683471679688,
      "learning_rate": 0.00011154846369695863,
      "loss": 0.4476,
      "step": 49
    },
    {
      "epoch": 0.0010057781957344947,
      "grad_norm": 2.396751642227173,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.6431,
      "step": 50
    },
    {
      "epoch": 0.0010057781957344947,
      "eval_loss": 0.380575567483902,
      "eval_runtime": 5967.1284,
      "eval_samples_per_second": 3.508,
      "eval_steps_per_second": 1.754,
      "step": 50
    },
    {
      "epoch": 0.0010258937596491846,
      "grad_norm": 0.38414570689201355,
      "learning_rate": 0.00010495837546732224,
      "loss": 0.2282,
      "step": 51
    },
    {
      "epoch": 0.0010460093235638746,
      "grad_norm": 0.3211899995803833,
      "learning_rate": 0.00010165339447663587,
      "loss": 0.1184,
      "step": 52
    },
    {
      "epoch": 0.0010661248874785643,
      "grad_norm": 0.9627249836921692,
      "learning_rate": 9.834660552336415e-05,
      "loss": 0.4364,
      "step": 53
    },
    {
      "epoch": 0.0010862404513932542,
      "grad_norm": 0.7375980615615845,
      "learning_rate": 9.504162453267777e-05,
      "loss": 0.3803,
      "step": 54
    },
    {
      "epoch": 0.0011063560153079441,
      "grad_norm": 0.5468074083328247,
      "learning_rate": 9.174206545276677e-05,
      "loss": 0.2981,
      "step": 55
    },
    {
      "epoch": 0.001126471579222634,
      "grad_norm": 0.7391518950462341,
      "learning_rate": 8.845153630304139e-05,
      "loss": 0.1971,
      "step": 56
    },
    {
      "epoch": 0.001146587143137324,
      "grad_norm": 0.7402855157852173,
      "learning_rate": 8.517363522881579e-05,
      "loss": 0.369,
      "step": 57
    },
    {
      "epoch": 0.0011667027070520139,
      "grad_norm": 0.6873307228088379,
      "learning_rate": 8.191194656678904e-05,
      "loss": 0.2407,
      "step": 58
    },
    {
      "epoch": 0.0011868182709667038,
      "grad_norm": 0.8516045808792114,
      "learning_rate": 7.867003692562534e-05,
      "loss": 0.456,
      "step": 59
    },
    {
      "epoch": 0.0012069338348813937,
      "grad_norm": 0.7615935802459717,
      "learning_rate": 7.54514512859201e-05,
      "loss": 0.3219,
      "step": 60
    },
    {
      "epoch": 0.0012270493987960834,
      "grad_norm": 0.8060344457626343,
      "learning_rate": 7.225970912381556e-05,
      "loss": 0.3268,
      "step": 61
    },
    {
      "epoch": 0.0012471649627107733,
      "grad_norm": 0.8558330535888672,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.3541,
      "step": 62
    },
    {
      "epoch": 0.0012672805266254633,
      "grad_norm": 0.6157307028770447,
      "learning_rate": 6.59706825558357e-05,
      "loss": 0.2617,
      "step": 63
    },
    {
      "epoch": 0.0012873960905401532,
      "grad_norm": 0.7628781795501709,
      "learning_rate": 6.28802751081779e-05,
      "loss": 0.2967,
      "step": 64
    },
    {
      "epoch": 0.001307511654454843,
      "grad_norm": 0.7932960391044617,
      "learning_rate": 5.983045753470308e-05,
      "loss": 0.1853,
      "step": 65
    },
    {
      "epoch": 0.001327627218369533,
      "grad_norm": 0.81103515625,
      "learning_rate": 5.6824564766150726e-05,
      "loss": 0.4439,
      "step": 66
    },
    {
      "epoch": 0.001347742782284223,
      "grad_norm": 0.5632208585739136,
      "learning_rate": 5.386588370213124e-05,
      "loss": 0.1508,
      "step": 67
    },
    {
      "epoch": 0.0013678583461989129,
      "grad_norm": 2.1608479022979736,
      "learning_rate": 5.095764961694922e-05,
      "loss": 0.7052,
      "step": 68
    },
    {
      "epoch": 0.0013879739101136026,
      "grad_norm": 0.8930830955505371,
      "learning_rate": 4.810304262187852e-05,
      "loss": 0.3767,
      "step": 69
    },
    {
      "epoch": 0.0014080894740282925,
      "grad_norm": 0.8396534323692322,
      "learning_rate": 4.530518418775733e-05,
      "loss": 0.2262,
      "step": 70
    },
    {
      "epoch": 0.0014282050379429824,
      "grad_norm": 0.8134317398071289,
      "learning_rate": 4.256713373170564e-05,
      "loss": 0.3279,
      "step": 71
    },
    {
      "epoch": 0.0014483206018576723,
      "grad_norm": 0.5932597517967224,
      "learning_rate": 3.9891885271697496e-05,
      "loss": 0.1684,
      "step": 72
    },
    {
      "epoch": 0.0014684361657723622,
      "grad_norm": 0.533363401889801,
      "learning_rate": 3.7282364152646297e-05,
      "loss": 0.1556,
      "step": 73
    },
    {
      "epoch": 0.0014885517296870522,
      "grad_norm": 1.1344701051712036,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 0.4778,
      "step": 74
    },
    {
      "epoch": 0.001508667293601742,
      "grad_norm": 0.5955411791801453,
      "learning_rate": 3.227184283742591e-05,
      "loss": 0.2269,
      "step": 75
    },
    {
      "epoch": 0.001508667293601742,
      "eval_loss": 0.35070064663887024,
      "eval_runtime": 5966.9045,
      "eval_samples_per_second": 3.508,
      "eval_steps_per_second": 1.754,
      "step": 75
    },
    {
      "epoch": 0.001528782857516432,
      "grad_norm": 0.6691503524780273,
      "learning_rate": 2.9876321572751144e-05,
      "loss": 0.1867,
      "step": 76
    },
    {
      "epoch": 0.0015488984214311217,
      "grad_norm": 1.2199984788894653,
      "learning_rate": 2.7557479520891104e-05,
      "loss": 0.2102,
      "step": 77
    },
    {
      "epoch": 0.0015690139853458116,
      "grad_norm": 0.6254073977470398,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 0.1688,
      "step": 78
    },
    {
      "epoch": 0.0015891295492605016,
      "grad_norm": 0.7005298137664795,
      "learning_rate": 2.315988891431412e-05,
      "loss": 0.1579,
      "step": 79
    },
    {
      "epoch": 0.0016092451131751915,
      "grad_norm": 0.359977662563324,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 0.0562,
      "step": 80
    },
    {
      "epoch": 0.0016293606770898814,
      "grad_norm": 1.038337230682373,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.1723,
      "step": 81
    },
    {
      "epoch": 0.0016494762410045713,
      "grad_norm": 0.537745475769043,
      "learning_rate": 1.7199116885197995e-05,
      "loss": 0.0839,
      "step": 82
    },
    {
      "epoch": 0.0016695918049192612,
      "grad_norm": 0.7610992789268494,
      "learning_rate": 1.5390474757906446e-05,
      "loss": 0.1321,
      "step": 83
    },
    {
      "epoch": 0.0016897073688339512,
      "grad_norm": 0.8755677342414856,
      "learning_rate": 1.3674351904242611e-05,
      "loss": 0.158,
      "step": 84
    },
    {
      "epoch": 0.0017098229327486409,
      "grad_norm": 1.5665292739868164,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 0.3811,
      "step": 85
    },
    {
      "epoch": 0.0017299384966633308,
      "grad_norm": 0.665432333946228,
      "learning_rate": 1.0527067017923654e-05,
      "loss": 0.1981,
      "step": 86
    },
    {
      "epoch": 0.0017500540605780207,
      "grad_norm": 0.6402338147163391,
      "learning_rate": 9.09934649508375e-06,
      "loss": 0.1776,
      "step": 87
    },
    {
      "epoch": 0.0017701696244927106,
      "grad_norm": 1.7284150123596191,
      "learning_rate": 7.771024502261526e-06,
      "loss": 0.4189,
      "step": 88
    },
    {
      "epoch": 0.0017902851884074005,
      "grad_norm": 0.9359285831451416,
      "learning_rate": 6.543553540053926e-06,
      "loss": 0.1095,
      "step": 89
    },
    {
      "epoch": 0.0018104007523220905,
      "grad_norm": 0.8026375770568848,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.1492,
      "step": 90
    },
    {
      "epoch": 0.0018305163162367804,
      "grad_norm": 2.1033782958984375,
      "learning_rate": 4.3964218465642355e-06,
      "loss": 0.4742,
      "step": 91
    },
    {
      "epoch": 0.0018506318801514703,
      "grad_norm": 3.3076441287994385,
      "learning_rate": 3.4791089722651436e-06,
      "loss": 0.4197,
      "step": 92
    },
    {
      "epoch": 0.00187074744406616,
      "grad_norm": 2.0006370544433594,
      "learning_rate": 2.667340275199426e-06,
      "loss": 0.5587,
      "step": 93
    },
    {
      "epoch": 0.00189086300798085,
      "grad_norm": 1.3604930639266968,
      "learning_rate": 1.9620034125190644e-06,
      "loss": 0.4432,
      "step": 94
    },
    {
      "epoch": 0.0019109785718955398,
      "grad_norm": 1.7596443891525269,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 0.4846,
      "step": 95
    },
    {
      "epoch": 0.0019310941358102298,
      "grad_norm": 2.329746723175049,
      "learning_rate": 8.735930673024806e-07,
      "loss": 0.6485,
      "step": 96
    },
    {
      "epoch": 0.0019512096997249197,
      "grad_norm": 1.9191521406173706,
      "learning_rate": 4.917097454988584e-07,
      "loss": 0.2235,
      "step": 97
    },
    {
      "epoch": 0.0019713252636396096,
      "grad_norm": 2.7021889686584473,
      "learning_rate": 2.1863727812254653e-07,
      "loss": 0.7207,
      "step": 98
    },
    {
      "epoch": 0.0019914408275542995,
      "grad_norm": 2.9134979248046875,
      "learning_rate": 5.467426590739511e-08,
      "loss": 0.8107,
      "step": 99
    },
    {
      "epoch": 0.0020115563914689895,
      "grad_norm": 1.8843333721160889,
      "learning_rate": 0.0,
      "loss": 0.4125,
      "step": 100
    },
    {
      "epoch": 0.0020115563914689895,
      "eval_loss": 0.3503866195678711,
      "eval_runtime": 5962.3258,
      "eval_samples_per_second": 3.511,
      "eval_steps_per_second": 1.755,
      "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": 1.4874840035386982e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}