{
  "best_metric": 11.747422218322754,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.5037783375314862,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005037783375314861,
      "grad_norm": 0.11665327101945877,
      "learning_rate": 4e-05,
      "loss": 11.7818,
      "step": 1
    },
    {
      "epoch": 0.005037783375314861,
      "eval_loss": 11.777442932128906,
      "eval_runtime": 1.3844,
      "eval_samples_per_second": 60.678,
      "eval_steps_per_second": 30.339,
      "step": 1
    },
    {
      "epoch": 0.010075566750629723,
      "grad_norm": 0.09411647170782089,
      "learning_rate": 8e-05,
      "loss": 11.7749,
      "step": 2
    },
    {
      "epoch": 0.015113350125944584,
      "grad_norm": 0.11491205543279648,
      "learning_rate": 0.00012,
      "loss": 11.7791,
      "step": 3
    },
    {
      "epoch": 0.020151133501259445,
      "grad_norm": 0.10814717411994934,
      "learning_rate": 0.00016,
      "loss": 11.7724,
      "step": 4
    },
    {
      "epoch": 0.02518891687657431,
      "grad_norm": 0.09395021945238113,
      "learning_rate": 0.0002,
      "loss": 11.7741,
      "step": 5
    },
    {
      "epoch": 0.030226700251889168,
      "grad_norm": 0.08854291588068008,
      "learning_rate": 0.00019994532573409262,
      "loss": 11.7739,
      "step": 6
    },
    {
      "epoch": 0.03526448362720403,
      "grad_norm": 0.09998143464326859,
      "learning_rate": 0.00019978136272187747,
      "loss": 11.7719,
      "step": 7
    },
    {
      "epoch": 0.04030226700251889,
      "grad_norm": 0.1092071384191513,
      "learning_rate": 0.00019950829025450114,
      "loss": 11.7766,
      "step": 8
    },
    {
      "epoch": 0.04534005037783375,
      "grad_norm": 0.13437338173389435,
      "learning_rate": 0.00019912640693269752,
      "loss": 11.7695,
      "step": 9
    },
    {
      "epoch": 0.05037783375314862,
      "grad_norm": 0.10191803425550461,
      "learning_rate": 0.00019863613034027224,
      "loss": 11.7726,
      "step": 10
    },
    {
      "epoch": 0.055415617128463476,
      "grad_norm": 0.13112697005271912,
      "learning_rate": 0.00019803799658748094,
      "loss": 11.7715,
      "step": 11
    },
    {
      "epoch": 0.060453400503778336,
      "grad_norm": 0.1708078533411026,
      "learning_rate": 0.0001973326597248006,
      "loss": 11.765,
      "step": 12
    },
    {
      "epoch": 0.0654911838790932,
      "grad_norm": 0.14378079771995544,
      "learning_rate": 0.00019652089102773488,
      "loss": 11.7693,
      "step": 13
    },
    {
      "epoch": 0.07052896725440806,
      "grad_norm": 0.11845815926790237,
      "learning_rate": 0.00019560357815343577,
      "loss": 11.754,
      "step": 14
    },
    {
      "epoch": 0.07556675062972293,
      "grad_norm": 0.13851119577884674,
      "learning_rate": 0.00019458172417006347,
      "loss": 11.7614,
      "step": 15
    },
    {
      "epoch": 0.08060453400503778,
      "grad_norm": 0.14140120148658752,
      "learning_rate": 0.0001934564464599461,
      "loss": 11.7656,
      "step": 16
    },
    {
      "epoch": 0.08564231738035265,
      "grad_norm": 0.21620717644691467,
      "learning_rate": 0.00019222897549773848,
      "loss": 11.7735,
      "step": 17
    },
    {
      "epoch": 0.0906801007556675,
      "grad_norm": 0.2548966407775879,
      "learning_rate": 0.00019090065350491626,
      "loss": 11.775,
      "step": 18
    },
    {
      "epoch": 0.09571788413098237,
      "grad_norm": 0.2564621865749359,
      "learning_rate": 0.00018947293298207635,
      "loss": 11.7763,
      "step": 19
    },
    {
      "epoch": 0.10075566750629723,
      "grad_norm": 0.24637818336486816,
      "learning_rate": 0.0001879473751206489,
      "loss": 11.7768,
      "step": 20
    },
    {
      "epoch": 0.10579345088161209,
      "grad_norm": 0.20252592861652374,
      "learning_rate": 0.00018632564809575742,
      "loss": 11.7709,
      "step": 21
    },
    {
      "epoch": 0.11083123425692695,
      "grad_norm": 0.1991090625524521,
      "learning_rate": 0.00018460952524209355,
      "loss": 11.77,
      "step": 22
    },
    {
      "epoch": 0.11586901763224182,
      "grad_norm": 0.19447946548461914,
      "learning_rate": 0.00018280088311480201,
      "loss": 11.7763,
      "step": 23
    },
    {
      "epoch": 0.12090680100755667,
      "grad_norm": 0.31570008397102356,
      "learning_rate": 0.00018090169943749476,
      "loss": 11.7832,
      "step": 24
    },
    {
      "epoch": 0.12594458438287154,
      "grad_norm": 0.26807549595832825,
      "learning_rate": 0.00017891405093963938,
      "loss": 11.781,
      "step": 25
    },
    {
      "epoch": 0.1309823677581864,
      "grad_norm": 0.20723332464694977,
      "learning_rate": 0.00017684011108568592,
      "loss": 11.7613,
      "step": 26
    },
    {
      "epoch": 0.13602015113350127,
      "grad_norm": 0.16287362575531006,
      "learning_rate": 0.0001746821476984154,
      "loss": 11.7537,
      "step": 27
    },
    {
      "epoch": 0.14105793450881612,
      "grad_norm": 0.19770941138267517,
      "learning_rate": 0.00017244252047910892,
      "loss": 11.7782,
      "step": 28
    },
    {
      "epoch": 0.14609571788413098,
      "grad_norm": 0.20761863887310028,
      "learning_rate": 0.00017012367842724887,
      "loss": 11.758,
      "step": 29
    },
    {
      "epoch": 0.15113350125944586,
      "grad_norm": 0.25872254371643066,
      "learning_rate": 0.00016772815716257412,
      "loss": 11.7536,
      "step": 30
    },
    {
      "epoch": 0.1561712846347607,
      "grad_norm": 0.3000946342945099,
      "learning_rate": 0.00016525857615241687,
      "loss": 11.7583,
      "step": 31
    },
    {
      "epoch": 0.16120906801007556,
      "grad_norm": 0.2385156750679016,
      "learning_rate": 0.0001627176358473537,
      "loss": 11.7501,
      "step": 32
    },
    {
      "epoch": 0.16624685138539042,
      "grad_norm": 0.2373785525560379,
      "learning_rate": 0.00016010811472830252,
      "loss": 11.7478,
      "step": 33
    },
    {
      "epoch": 0.1712846347607053,
      "grad_norm": 0.5123424530029297,
      "learning_rate": 0.00015743286626829437,
      "loss": 11.788,
      "step": 34
    },
    {
      "epoch": 0.17632241813602015,
      "grad_norm": 0.4221782386302948,
      "learning_rate": 0.00015469481581224272,
      "loss": 11.7738,
      "step": 35
    },
    {
      "epoch": 0.181360201511335,
      "grad_norm": 0.3816068768501282,
      "learning_rate": 0.00015189695737812152,
      "loss": 11.771,
      "step": 36
    },
    {
      "epoch": 0.18639798488664988,
      "grad_norm": 0.34051746129989624,
      "learning_rate": 0.00014904235038305083,
      "loss": 11.7577,
      "step": 37
    },
    {
      "epoch": 0.19143576826196473,
      "grad_norm": 0.2573257386684418,
      "learning_rate": 0.0001461341162978688,
      "loss": 11.7447,
      "step": 38
    },
    {
      "epoch": 0.1964735516372796,
      "grad_norm": 0.5065600275993347,
      "learning_rate": 0.00014317543523384928,
      "loss": 11.7931,
      "step": 39
    },
    {
      "epoch": 0.20151133501259447,
      "grad_norm": 0.48842620849609375,
      "learning_rate": 0.00014016954246529696,
      "loss": 11.7782,
      "step": 40
    },
    {
      "epoch": 0.20654911838790932,
      "grad_norm": 0.5999230742454529,
      "learning_rate": 0.00013711972489182208,
      "loss": 11.7796,
      "step": 41
    },
    {
      "epoch": 0.21158690176322417,
      "grad_norm": 0.5456677079200745,
      "learning_rate": 0.00013402931744416433,
      "loss": 11.7846,
      "step": 42
    },
    {
      "epoch": 0.21662468513853905,
      "grad_norm": 0.544049859046936,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.7765,
      "step": 43
    },
    {
      "epoch": 0.2216624685138539,
      "grad_norm": 0.4290430545806885,
      "learning_rate": 0.00012774029087618446,
      "loss": 11.7786,
      "step": 44
    },
    {
      "epoch": 0.22670025188916876,
      "grad_norm": 0.624894380569458,
      "learning_rate": 0.00012454854871407994,
      "loss": 11.7792,
      "step": 45
    },
    {
      "epoch": 0.23173803526448364,
      "grad_norm": 0.6616364121437073,
      "learning_rate": 0.0001213299630743747,
      "loss": 11.7779,
      "step": 46
    },
    {
      "epoch": 0.2367758186397985,
      "grad_norm": 0.6500002145767212,
      "learning_rate": 0.000118088053433211,
      "loss": 11.7756,
      "step": 47
    },
    {
      "epoch": 0.24181360201511334,
      "grad_norm": 0.7946918606758118,
      "learning_rate": 0.0001148263647711842,
      "loss": 11.7614,
      "step": 48
    },
    {
      "epoch": 0.24685138539042822,
      "grad_norm": 0.7269666790962219,
      "learning_rate": 0.00011154846369695863,
      "loss": 11.7358,
      "step": 49
    },
    {
      "epoch": 0.2518891687657431,
      "grad_norm": 0.14651153981685638,
      "learning_rate": 0.00010825793454723325,
      "loss": 11.7679,
      "step": 50
    },
    {
      "epoch": 0.2518891687657431,
      "eval_loss": 11.756505966186523,
      "eval_runtime": 1.3815,
      "eval_samples_per_second": 60.803,
      "eval_steps_per_second": 30.401,
      "step": 50
    },
    {
      "epoch": 0.25692695214105793,
      "grad_norm": 0.12329468876123428,
      "learning_rate": 0.00010495837546732224,
      "loss": 11.7644,
      "step": 51
    },
    {
      "epoch": 0.2619647355163728,
      "grad_norm": 0.19282935559749603,
      "learning_rate": 0.00010165339447663587,
      "loss": 11.7626,
      "step": 52
    },
    {
      "epoch": 0.26700251889168763,
      "grad_norm": 0.13012297451496124,
      "learning_rate": 9.834660552336415e-05,
      "loss": 11.7701,
      "step": 53
    },
    {
      "epoch": 0.27204030226700254,
      "grad_norm": 0.1542385220527649,
      "learning_rate": 9.504162453267777e-05,
      "loss": 11.748,
      "step": 54
    },
    {
      "epoch": 0.2770780856423174,
      "grad_norm": 0.13558229804039001,
      "learning_rate": 9.174206545276677e-05,
      "loss": 11.7566,
      "step": 55
    },
    {
      "epoch": 0.28211586901763225,
      "grad_norm": 0.1677481085062027,
      "learning_rate": 8.845153630304139e-05,
      "loss": 11.7563,
      "step": 56
    },
    {
      "epoch": 0.2871536523929471,
      "grad_norm": 0.20597466826438904,
      "learning_rate": 8.517363522881579e-05,
      "loss": 11.7526,
      "step": 57
    },
    {
      "epoch": 0.29219143576826195,
      "grad_norm": 0.17000000178813934,
      "learning_rate": 8.191194656678904e-05,
      "loss": 11.7474,
      "step": 58
    },
    {
      "epoch": 0.2972292191435768,
      "grad_norm": 0.2849511206150055,
      "learning_rate": 7.867003692562534e-05,
      "loss": 11.7591,
      "step": 59
    },
    {
      "epoch": 0.3022670025188917,
      "grad_norm": 0.19527281820774078,
      "learning_rate": 7.54514512859201e-05,
      "loss": 11.7456,
      "step": 60
    },
    {
      "epoch": 0.30730478589420657,
      "grad_norm": 0.25237226486206055,
      "learning_rate": 7.225970912381556e-05,
      "loss": 11.7602,
      "step": 61
    },
    {
      "epoch": 0.3123425692695214,
      "grad_norm": 0.24200652539730072,
      "learning_rate": 6.909830056250527e-05,
      "loss": 11.7528,
      "step": 62
    },
    {
      "epoch": 0.31738035264483627,
      "grad_norm": 0.19608649611473083,
      "learning_rate": 6.59706825558357e-05,
      "loss": 11.7477,
      "step": 63
    },
    {
      "epoch": 0.3224181360201511,
      "grad_norm": 0.2160205841064453,
      "learning_rate": 6.28802751081779e-05,
      "loss": 11.7498,
      "step": 64
    },
    {
      "epoch": 0.327455919395466,
      "grad_norm": 0.3006030321121216,
      "learning_rate": 5.983045753470308e-05,
      "loss": 11.7526,
      "step": 65
    },
    {
      "epoch": 0.33249370277078083,
      "grad_norm": 0.2874875068664551,
      "learning_rate": 5.6824564766150726e-05,
      "loss": 11.7516,
      "step": 66
    },
    {
      "epoch": 0.33753148614609574,
      "grad_norm": 0.34401634335517883,
      "learning_rate": 5.386588370213124e-05,
      "loss": 11.7539,
      "step": 67
    },
    {
      "epoch": 0.3425692695214106,
      "grad_norm": 0.33066168427467346,
      "learning_rate": 5.095764961694922e-05,
      "loss": 11.752,
      "step": 68
    },
    {
      "epoch": 0.34760705289672544,
      "grad_norm": 0.29201266169548035,
      "learning_rate": 4.810304262187852e-05,
      "loss": 11.743,
      "step": 69
    },
    {
      "epoch": 0.3526448362720403,
      "grad_norm": 0.34607893228530884,
      "learning_rate": 4.530518418775733e-05,
      "loss": 11.7538,
      "step": 70
    },
    {
      "epoch": 0.35768261964735515,
      "grad_norm": 0.2541449964046478,
      "learning_rate": 4.256713373170564e-05,
      "loss": 11.7628,
      "step": 71
    },
    {
      "epoch": 0.36272040302267,
      "grad_norm": 0.29604771733283997,
      "learning_rate": 3.9891885271697496e-05,
      "loss": 11.7578,
      "step": 72
    },
    {
      "epoch": 0.3677581863979849,
      "grad_norm": 0.3188517093658447,
      "learning_rate": 3.7282364152646297e-05,
      "loss": 11.7621,
      "step": 73
    },
    {
      "epoch": 0.37279596977329976,
      "grad_norm": 0.24045149981975555,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 11.7587,
      "step": 74
    },
    {
      "epoch": 0.3778337531486146,
      "grad_norm": 0.27738526463508606,
      "learning_rate": 3.227184283742591e-05,
      "loss": 11.7587,
      "step": 75
    },
    {
      "epoch": 0.38287153652392947,
      "grad_norm": 0.20490190386772156,
      "learning_rate": 2.9876321572751144e-05,
      "loss": 11.736,
      "step": 76
    },
    {
      "epoch": 0.3879093198992443,
      "grad_norm": 0.34930336475372314,
      "learning_rate": 2.7557479520891104e-05,
      "loss": 11.7466,
      "step": 77
    },
    {
      "epoch": 0.3929471032745592,
      "grad_norm": 0.3548698425292969,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 11.748,
      "step": 78
    },
    {
      "epoch": 0.3979848866498741,
      "grad_norm": 0.22995570302009583,
      "learning_rate": 2.315988891431412e-05,
      "loss": 11.7384,
      "step": 79
    },
    {
      "epoch": 0.40302267002518893,
      "grad_norm": 0.39114826917648315,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 11.7427,
      "step": 80
    },
    {
      "epoch": 0.4080604534005038,
      "grad_norm": 0.3221098482608795,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 11.7438,
      "step": 81
    },
    {
      "epoch": 0.41309823677581864,
      "grad_norm": 0.5230813026428223,
      "learning_rate": 1.7199116885197995e-05,
      "loss": 11.7491,
      "step": 82
    },
    {
      "epoch": 0.4181360201511335,
      "grad_norm": 0.5868245363235474,
      "learning_rate": 1.5390474757906446e-05,
      "loss": 11.7492,
      "step": 83
    },
    {
      "epoch": 0.42317380352644834,
      "grad_norm": 0.7091190218925476,
      "learning_rate": 1.3674351904242611e-05,
      "loss": 11.7395,
      "step": 84
    },
    {
      "epoch": 0.4282115869017632,
      "grad_norm": 0.34904906153678894,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 11.7469,
      "step": 85
    },
    {
      "epoch": 0.4332493702770781,
      "grad_norm": 0.497840017080307,
      "learning_rate": 1.0527067017923654e-05,
      "loss": 11.7541,
      "step": 86
    },
    {
      "epoch": 0.43828715365239296,
      "grad_norm": 0.6534344553947449,
      "learning_rate": 9.09934649508375e-06,
      "loss": 11.7602,
      "step": 87
    },
    {
      "epoch": 0.4433249370277078,
      "grad_norm": 0.6424288749694824,
      "learning_rate": 7.771024502261526e-06,
      "loss": 11.7518,
      "step": 88
    },
    {
      "epoch": 0.44836272040302266,
      "grad_norm": 0.6290802955627441,
      "learning_rate": 6.543553540053926e-06,
      "loss": 11.7363,
      "step": 89
    },
    {
      "epoch": 0.4534005037783375,
      "grad_norm": 0.6020405292510986,
      "learning_rate": 5.418275829936537e-06,
      "loss": 11.7478,
      "step": 90
    },
    {
      "epoch": 0.45843828715365237,
      "grad_norm": 0.5933429002761841,
      "learning_rate": 4.3964218465642355e-06,
      "loss": 11.7431,
      "step": 91
    },
    {
      "epoch": 0.4634760705289673,
      "grad_norm": 0.7595274448394775,
      "learning_rate": 3.4791089722651436e-06,
      "loss": 11.746,
      "step": 92
    },
    {
      "epoch": 0.46851385390428213,
      "grad_norm": 0.7738293409347534,
      "learning_rate": 2.667340275199426e-06,
      "loss": 11.7478,
      "step": 93
    },
    {
      "epoch": 0.473551637279597,
      "grad_norm": 0.6566546559333801,
      "learning_rate": 1.9620034125190644e-06,
      "loss": 11.7331,
      "step": 94
    },
    {
      "epoch": 0.47858942065491183,
      "grad_norm": 0.790342390537262,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 11.7377,
      "step": 95
    },
    {
      "epoch": 0.4836272040302267,
      "grad_norm": 0.7581157684326172,
      "learning_rate": 8.735930673024806e-07,
      "loss": 11.7515,
      "step": 96
    },
    {
      "epoch": 0.48866498740554154,
      "grad_norm": 0.8844296932220459,
      "learning_rate": 4.917097454988584e-07,
      "loss": 11.715,
      "step": 97
    },
    {
      "epoch": 0.49370277078085645,
      "grad_norm": 0.9089491963386536,
      "learning_rate": 2.1863727812254653e-07,
      "loss": 11.7192,
      "step": 98
    },
    {
      "epoch": 0.4987405541561713,
      "grad_norm": 0.14338494837284088,
      "learning_rate": 5.467426590739511e-08,
      "loss": 11.7708,
      "step": 99
    },
    {
      "epoch": 0.5037783375314862,
      "grad_norm": 0.16467101871967316,
      "learning_rate": 0.0,
      "loss": 11.7612,
      "step": 100
    },
    {
      "epoch": 0.5037783375314862,
      "eval_loss": 11.747422218322754,
      "eval_runtime": 1.3803,
      "eval_samples_per_second": 60.857,
      "eval_steps_per_second": 30.429,
      "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": 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": 40740008755200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}