{
  "best_metric": 2.6855108737945557,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.014773776546629732,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014773776546629733,
      "grad_norm": 0.1680404245853424,
      "learning_rate": 4e-05,
      "loss": 2.2693,
      "step": 1
    },
    {
      "epoch": 0.00014773776546629733,
      "eval_loss": 2.8410422801971436,
      "eval_runtime": 245.1756,
      "eval_samples_per_second": 11.624,
      "eval_steps_per_second": 5.812,
      "step": 1
    },
    {
      "epoch": 0.00029547553093259467,
      "grad_norm": 0.24187016487121582,
      "learning_rate": 8e-05,
      "loss": 2.3835,
      "step": 2
    },
    {
      "epoch": 0.00044321329639889195,
      "grad_norm": 0.27124741673469543,
      "learning_rate": 0.00012,
      "loss": 2.5753,
      "step": 3
    },
    {
      "epoch": 0.0005909510618651893,
      "grad_norm": 0.32595115900039673,
      "learning_rate": 0.00016,
      "loss": 2.4737,
      "step": 4
    },
    {
      "epoch": 0.0007386888273314866,
      "grad_norm": 0.3274131715297699,
      "learning_rate": 0.0002,
      "loss": 2.5374,
      "step": 5
    },
    {
      "epoch": 0.0008864265927977839,
      "grad_norm": 0.31691431999206543,
      "learning_rate": 0.00019994532573409262,
      "loss": 2.6162,
      "step": 6
    },
    {
      "epoch": 0.0010341643582640813,
      "grad_norm": 0.35264068841934204,
      "learning_rate": 0.00019978136272187747,
      "loss": 2.5054,
      "step": 7
    },
    {
      "epoch": 0.0011819021237303787,
      "grad_norm": 0.39142340421676636,
      "learning_rate": 0.00019950829025450114,
      "loss": 2.565,
      "step": 8
    },
    {
      "epoch": 0.001329639889196676,
      "grad_norm": 0.3724002242088318,
      "learning_rate": 0.00019912640693269752,
      "loss": 2.5553,
      "step": 9
    },
    {
      "epoch": 0.0014773776546629731,
      "grad_norm": 0.5595511794090271,
      "learning_rate": 0.00019863613034027224,
      "loss": 2.5109,
      "step": 10
    },
    {
      "epoch": 0.0016251154201292705,
      "grad_norm": 0.4720703959465027,
      "learning_rate": 0.00019803799658748094,
      "loss": 2.6227,
      "step": 11
    },
    {
      "epoch": 0.0017728531855955678,
      "grad_norm": 0.428568571805954,
      "learning_rate": 0.0001973326597248006,
      "loss": 2.5642,
      "step": 12
    },
    {
      "epoch": 0.0019205909510618651,
      "grad_norm": 0.523729681968689,
      "learning_rate": 0.00019652089102773488,
      "loss": 2.5874,
      "step": 13
    },
    {
      "epoch": 0.0020683287165281627,
      "grad_norm": 0.48841235041618347,
      "learning_rate": 0.00019560357815343577,
      "loss": 2.4838,
      "step": 14
    },
    {
      "epoch": 0.00221606648199446,
      "grad_norm": 0.5847761034965515,
      "learning_rate": 0.00019458172417006347,
      "loss": 2.5853,
      "step": 15
    },
    {
      "epoch": 0.0023638042474607573,
      "grad_norm": 0.5334342122077942,
      "learning_rate": 0.0001934564464599461,
      "loss": 2.6511,
      "step": 16
    },
    {
      "epoch": 0.0025115420129270547,
      "grad_norm": 0.5539087057113647,
      "learning_rate": 0.00019222897549773848,
      "loss": 2.5072,
      "step": 17
    },
    {
      "epoch": 0.002659279778393352,
      "grad_norm": 0.5858405828475952,
      "learning_rate": 0.00019090065350491626,
      "loss": 2.7543,
      "step": 18
    },
    {
      "epoch": 0.002807017543859649,
      "grad_norm": 0.6383663415908813,
      "learning_rate": 0.00018947293298207635,
      "loss": 2.9209,
      "step": 19
    },
    {
      "epoch": 0.0029547553093259462,
      "grad_norm": 0.5604156851768494,
      "learning_rate": 0.0001879473751206489,
      "loss": 2.5698,
      "step": 20
    },
    {
      "epoch": 0.0031024930747922436,
      "grad_norm": 0.5957999229431152,
      "learning_rate": 0.00018632564809575742,
      "loss": 2.6138,
      "step": 21
    },
    {
      "epoch": 0.003250230840258541,
      "grad_norm": 0.7011343836784363,
      "learning_rate": 0.00018460952524209355,
      "loss": 2.6191,
      "step": 22
    },
    {
      "epoch": 0.0033979686057248383,
      "grad_norm": 0.6490035653114319,
      "learning_rate": 0.00018280088311480201,
      "loss": 2.7153,
      "step": 23
    },
    {
      "epoch": 0.0035457063711911356,
      "grad_norm": 0.7848305106163025,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.6823,
      "step": 24
    },
    {
      "epoch": 0.003693444136657433,
      "grad_norm": 0.7075931429862976,
      "learning_rate": 0.00017891405093963938,
      "loss": 2.5126,
      "step": 25
    },
    {
      "epoch": 0.003693444136657433,
      "eval_loss": 2.715409517288208,
      "eval_runtime": 245.526,
      "eval_samples_per_second": 11.608,
      "eval_steps_per_second": 5.804,
      "step": 25
    },
    {
      "epoch": 0.0038411819021237303,
      "grad_norm": 0.8052982687950134,
      "learning_rate": 0.00017684011108568592,
      "loss": 2.8032,
      "step": 26
    },
    {
      "epoch": 0.003988919667590028,
      "grad_norm": 0.7346736192703247,
      "learning_rate": 0.0001746821476984154,
      "loss": 2.5539,
      "step": 27
    },
    {
      "epoch": 0.004136657433056325,
      "grad_norm": 0.7615510821342468,
      "learning_rate": 0.00017244252047910892,
      "loss": 2.7599,
      "step": 28
    },
    {
      "epoch": 0.004284395198522623,
      "grad_norm": 0.8807427883148193,
      "learning_rate": 0.00017012367842724887,
      "loss": 2.6514,
      "step": 29
    },
    {
      "epoch": 0.00443213296398892,
      "grad_norm": 0.8408799171447754,
      "learning_rate": 0.00016772815716257412,
      "loss": 2.823,
      "step": 30
    },
    {
      "epoch": 0.004579870729455217,
      "grad_norm": 0.9535984992980957,
      "learning_rate": 0.00016525857615241687,
      "loss": 2.7928,
      "step": 31
    },
    {
      "epoch": 0.004727608494921515,
      "grad_norm": 0.931502640247345,
      "learning_rate": 0.0001627176358473537,
      "loss": 3.0296,
      "step": 32
    },
    {
      "epoch": 0.004875346260387812,
      "grad_norm": 0.9972584247589111,
      "learning_rate": 0.00016010811472830252,
      "loss": 2.7615,
      "step": 33
    },
    {
      "epoch": 0.005023084025854109,
      "grad_norm": 0.9503821730613708,
      "learning_rate": 0.00015743286626829437,
      "loss": 2.9016,
      "step": 34
    },
    {
      "epoch": 0.005170821791320407,
      "grad_norm": 0.8864520788192749,
      "learning_rate": 0.00015469481581224272,
      "loss": 3.2727,
      "step": 35
    },
    {
      "epoch": 0.005318559556786704,
      "grad_norm": 0.7939389944076538,
      "learning_rate": 0.00015189695737812152,
      "loss": 2.6502,
      "step": 36
    },
    {
      "epoch": 0.0054662973222530005,
      "grad_norm": 0.8255647420883179,
      "learning_rate": 0.00014904235038305083,
      "loss": 3.0277,
      "step": 37
    },
    {
      "epoch": 0.005614035087719298,
      "grad_norm": 0.9084526896476746,
      "learning_rate": 0.0001461341162978688,
      "loss": 2.8495,
      "step": 38
    },
    {
      "epoch": 0.005761772853185595,
      "grad_norm": 0.8007035255432129,
      "learning_rate": 0.00014317543523384928,
      "loss": 2.9053,
      "step": 39
    },
    {
      "epoch": 0.0059095106186518925,
      "grad_norm": 0.8639392852783203,
      "learning_rate": 0.00014016954246529696,
      "loss": 2.804,
      "step": 40
    },
    {
      "epoch": 0.00605724838411819,
      "grad_norm": 0.9926638603210449,
      "learning_rate": 0.00013711972489182208,
      "loss": 2.8584,
      "step": 41
    },
    {
      "epoch": 0.006204986149584487,
      "grad_norm": 0.9736136198043823,
      "learning_rate": 0.00013402931744416433,
      "loss": 2.8866,
      "step": 42
    },
    {
      "epoch": 0.0063527239150507845,
      "grad_norm": 0.8373548984527588,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.7566,
      "step": 43
    },
    {
      "epoch": 0.006500461680517082,
      "grad_norm": 0.8510177731513977,
      "learning_rate": 0.00012774029087618446,
      "loss": 2.8319,
      "step": 44
    },
    {
      "epoch": 0.006648199445983379,
      "grad_norm": 1.0112504959106445,
      "learning_rate": 0.00012454854871407994,
      "loss": 2.9611,
      "step": 45
    },
    {
      "epoch": 0.0067959372114496765,
      "grad_norm": 0.9748664498329163,
      "learning_rate": 0.0001213299630743747,
      "loss": 2.8568,
      "step": 46
    },
    {
      "epoch": 0.006943674976915974,
      "grad_norm": 0.935685396194458,
      "learning_rate": 0.000118088053433211,
      "loss": 2.8491,
      "step": 47
    },
    {
      "epoch": 0.007091412742382271,
      "grad_norm": 1.117539405822754,
      "learning_rate": 0.0001148263647711842,
      "loss": 3.2332,
      "step": 48
    },
    {
      "epoch": 0.0072391505078485685,
      "grad_norm": 1.5835413932800293,
      "learning_rate": 0.00011154846369695863,
      "loss": 2.9418,
      "step": 49
    },
    {
      "epoch": 0.007386888273314866,
      "grad_norm": 2.222666025161743,
      "learning_rate": 0.00010825793454723325,
      "loss": 2.7793,
      "step": 50
    },
    {
      "epoch": 0.007386888273314866,
      "eval_loss": 2.7024636268615723,
      "eval_runtime": 245.5234,
      "eval_samples_per_second": 11.608,
      "eval_steps_per_second": 5.804,
      "step": 50
    },
    {
      "epoch": 0.007534626038781163,
      "grad_norm": 0.41233178973197937,
      "learning_rate": 0.00010495837546732224,
      "loss": 2.283,
      "step": 51
    },
    {
      "epoch": 0.0076823638042474605,
      "grad_norm": 0.45200082659721375,
      "learning_rate": 0.00010165339447663587,
      "loss": 2.615,
      "step": 52
    },
    {
      "epoch": 0.007830101569713758,
      "grad_norm": 0.44340193271636963,
      "learning_rate": 9.834660552336415e-05,
      "loss": 2.2959,
      "step": 53
    },
    {
      "epoch": 0.007977839335180056,
      "grad_norm": 0.3993021547794342,
      "learning_rate": 9.504162453267777e-05,
      "loss": 2.5127,
      "step": 54
    },
    {
      "epoch": 0.008125577100646353,
      "grad_norm": 0.38962098956108093,
      "learning_rate": 9.174206545276677e-05,
      "loss": 2.6104,
      "step": 55
    },
    {
      "epoch": 0.00827331486611265,
      "grad_norm": 0.4015566408634186,
      "learning_rate": 8.845153630304139e-05,
      "loss": 2.3183,
      "step": 56
    },
    {
      "epoch": 0.008421052631578947,
      "grad_norm": 0.3686407804489136,
      "learning_rate": 8.517363522881579e-05,
      "loss": 2.4809,
      "step": 57
    },
    {
      "epoch": 0.008568790397045245,
      "grad_norm": 0.3890494704246521,
      "learning_rate": 8.191194656678904e-05,
      "loss": 2.7139,
      "step": 58
    },
    {
      "epoch": 0.008716528162511542,
      "grad_norm": 0.3961982727050781,
      "learning_rate": 7.867003692562534e-05,
      "loss": 2.6264,
      "step": 59
    },
    {
      "epoch": 0.00886426592797784,
      "grad_norm": 0.4162742495536804,
      "learning_rate": 7.54514512859201e-05,
      "loss": 2.4902,
      "step": 60
    },
    {
      "epoch": 0.009012003693444137,
      "grad_norm": 0.3902261257171631,
      "learning_rate": 7.225970912381556e-05,
      "loss": 2.5772,
      "step": 61
    },
    {
      "epoch": 0.009159741458910435,
      "grad_norm": 0.3940078616142273,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.6563,
      "step": 62
    },
    {
      "epoch": 0.009307479224376731,
      "grad_norm": 0.4395645558834076,
      "learning_rate": 6.59706825558357e-05,
      "loss": 2.6348,
      "step": 63
    },
    {
      "epoch": 0.00945521698984303,
      "grad_norm": 0.4575493335723877,
      "learning_rate": 6.28802751081779e-05,
      "loss": 2.5413,
      "step": 64
    },
    {
      "epoch": 0.009602954755309326,
      "grad_norm": 0.4489690065383911,
      "learning_rate": 5.983045753470308e-05,
      "loss": 2.4907,
      "step": 65
    },
    {
      "epoch": 0.009750692520775624,
      "grad_norm": 0.4150414764881134,
      "learning_rate": 5.6824564766150726e-05,
      "loss": 2.4324,
      "step": 66
    },
    {
      "epoch": 0.00989843028624192,
      "grad_norm": 0.46985292434692383,
      "learning_rate": 5.386588370213124e-05,
      "loss": 2.4636,
      "step": 67
    },
    {
      "epoch": 0.010046168051708219,
      "grad_norm": 0.4917268753051758,
      "learning_rate": 5.095764961694922e-05,
      "loss": 2.5561,
      "step": 68
    },
    {
      "epoch": 0.010193905817174515,
      "grad_norm": 0.5081900954246521,
      "learning_rate": 4.810304262187852e-05,
      "loss": 2.7343,
      "step": 69
    },
    {
      "epoch": 0.010341643582640813,
      "grad_norm": 0.4855806827545166,
      "learning_rate": 4.530518418775733e-05,
      "loss": 2.7617,
      "step": 70
    },
    {
      "epoch": 0.01048938134810711,
      "grad_norm": 0.5101497769355774,
      "learning_rate": 4.256713373170564e-05,
      "loss": 2.6342,
      "step": 71
    },
    {
      "epoch": 0.010637119113573408,
      "grad_norm": 0.5174307227134705,
      "learning_rate": 3.9891885271697496e-05,
      "loss": 2.7903,
      "step": 72
    },
    {
      "epoch": 0.010784856879039705,
      "grad_norm": 0.550068199634552,
      "learning_rate": 3.7282364152646297e-05,
      "loss": 2.6579,
      "step": 73
    },
    {
      "epoch": 0.010932594644506001,
      "grad_norm": 0.5740828514099121,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 2.6477,
      "step": 74
    },
    {
      "epoch": 0.0110803324099723,
      "grad_norm": 0.5267476439476013,
      "learning_rate": 3.227184283742591e-05,
      "loss": 2.7395,
      "step": 75
    },
    {
      "epoch": 0.0110803324099723,
      "eval_loss": 2.689473867416382,
      "eval_runtime": 245.5378,
      "eval_samples_per_second": 11.607,
      "eval_steps_per_second": 5.804,
      "step": 75
    },
    {
      "epoch": 0.011228070175438596,
      "grad_norm": 0.5013121962547302,
      "learning_rate": 2.9876321572751144e-05,
      "loss": 2.6454,
      "step": 76
    },
    {
      "epoch": 0.011375807940904894,
      "grad_norm": 0.6422709226608276,
      "learning_rate": 2.7557479520891104e-05,
      "loss": 2.7858,
      "step": 77
    },
    {
      "epoch": 0.01152354570637119,
      "grad_norm": 0.5303881764411926,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 2.5976,
      "step": 78
    },
    {
      "epoch": 0.011671283471837489,
      "grad_norm": 0.7301583290100098,
      "learning_rate": 2.315988891431412e-05,
      "loss": 2.5867,
      "step": 79
    },
    {
      "epoch": 0.011819021237303785,
      "grad_norm": 0.6291911005973816,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 2.7627,
      "step": 80
    },
    {
      "epoch": 0.011966759002770083,
      "grad_norm": 0.5394213795661926,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.6842,
      "step": 81
    },
    {
      "epoch": 0.01211449676823638,
      "grad_norm": 0.6252685189247131,
      "learning_rate": 1.7199116885197995e-05,
      "loss": 2.8988,
      "step": 82
    },
    {
      "epoch": 0.012262234533702678,
      "grad_norm": 0.607553243637085,
      "learning_rate": 1.5390474757906446e-05,
      "loss": 2.7113,
      "step": 83
    },
    {
      "epoch": 0.012409972299168974,
      "grad_norm": 0.6846975088119507,
      "learning_rate": 1.3674351904242611e-05,
      "loss": 2.6447,
      "step": 84
    },
    {
      "epoch": 0.012557710064635273,
      "grad_norm": 0.6939342021942139,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 2.9223,
      "step": 85
    },
    {
      "epoch": 0.012705447830101569,
      "grad_norm": 0.6672337651252747,
      "learning_rate": 1.0527067017923654e-05,
      "loss": 2.8346,
      "step": 86
    },
    {
      "epoch": 0.012853185595567867,
      "grad_norm": 0.7558186650276184,
      "learning_rate": 9.09934649508375e-06,
      "loss": 2.8925,
      "step": 87
    },
    {
      "epoch": 0.013000923361034164,
      "grad_norm": 0.7285046577453613,
      "learning_rate": 7.771024502261526e-06,
      "loss": 2.75,
      "step": 88
    },
    {
      "epoch": 0.013148661126500462,
      "grad_norm": 0.8400636315345764,
      "learning_rate": 6.543553540053926e-06,
      "loss": 2.8976,
      "step": 89
    },
    {
      "epoch": 0.013296398891966758,
      "grad_norm": 0.7853424549102783,
      "learning_rate": 5.418275829936537e-06,
      "loss": 3.1096,
      "step": 90
    },
    {
      "epoch": 0.013444136657433057,
      "grad_norm": 0.7648143172264099,
      "learning_rate": 4.3964218465642355e-06,
      "loss": 2.9453,
      "step": 91
    },
    {
      "epoch": 0.013591874422899353,
      "grad_norm": 0.8376665711402893,
      "learning_rate": 3.4791089722651436e-06,
      "loss": 2.8444,
      "step": 92
    },
    {
      "epoch": 0.013739612188365651,
      "grad_norm": 0.8066268563270569,
      "learning_rate": 2.667340275199426e-06,
      "loss": 2.993,
      "step": 93
    },
    {
      "epoch": 0.013887349953831948,
      "grad_norm": 0.9552287459373474,
      "learning_rate": 1.9620034125190644e-06,
      "loss": 2.8803,
      "step": 94
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 0.8276549577713013,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 2.8189,
      "step": 95
    },
    {
      "epoch": 0.014182825484764542,
      "grad_norm": 0.8577640056610107,
      "learning_rate": 8.735930673024806e-07,
      "loss": 3.1154,
      "step": 96
    },
    {
      "epoch": 0.01433056325023084,
      "grad_norm": 0.8612611889839172,
      "learning_rate": 4.917097454988584e-07,
      "loss": 2.4841,
      "step": 97
    },
    {
      "epoch": 0.014478301015697137,
      "grad_norm": 0.9725845456123352,
      "learning_rate": 2.1863727812254653e-07,
      "loss": 2.7285,
      "step": 98
    },
    {
      "epoch": 0.014626038781163435,
      "grad_norm": 1.032256841659546,
      "learning_rate": 5.467426590739511e-08,
      "loss": 3.125,
      "step": 99
    },
    {
      "epoch": 0.014773776546629732,
      "grad_norm": 1.573689341545105,
      "learning_rate": 0.0,
      "loss": 2.9277,
      "step": 100
    },
    {
      "epoch": 0.014773776546629732,
      "eval_loss": 2.6855108737945557,
      "eval_runtime": 245.6241,
      "eval_samples_per_second": 11.603,
      "eval_steps_per_second": 5.802,
      "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": 2.5458351538176e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}