{
  "best_metric": 0.10608438402414322,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.2720348204570185,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000544069640914037,
      "eval_loss": 0.3388690948486328,
      "eval_runtime": 65.0573,
      "eval_samples_per_second": 5.949,
      "eval_steps_per_second": 1.491,
      "step": 1
    },
    {
      "epoch": 0.00544069640914037,
      "grad_norm": 0.17373442649841309,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 0.2499,
      "step": 10
    },
    {
      "epoch": 0.01088139281828074,
      "grad_norm": 0.2752276062965393,
      "learning_rate": 8.400000000000001e-05,
      "loss": 0.2266,
      "step": 20
    },
    {
      "epoch": 0.01632208922742111,
      "grad_norm": 0.2970355451107025,
      "learning_rate": 0.000126,
      "loss": 0.1705,
      "step": 30
    },
    {
      "epoch": 0.02176278563656148,
      "grad_norm": 0.2946202754974365,
      "learning_rate": 0.00016800000000000002,
      "loss": 0.1953,
      "step": 40
    },
    {
      "epoch": 0.02720348204570185,
      "grad_norm": 0.16966816782951355,
      "learning_rate": 0.00021,
      "loss": 0.1967,
      "step": 50
    },
    {
      "epoch": 0.02720348204570185,
      "eval_loss": 0.14745917916297913,
      "eval_runtime": 65.2419,
      "eval_samples_per_second": 5.932,
      "eval_steps_per_second": 1.487,
      "step": 50
    },
    {
      "epoch": 0.03264417845484222,
      "grad_norm": 0.2769581973552704,
      "learning_rate": 0.00020974422527728155,
      "loss": 0.1933,
      "step": 60
    },
    {
      "epoch": 0.03808487486398259,
      "grad_norm": 0.4267159104347229,
      "learning_rate": 0.0002089781472178649,
      "loss": 0.2355,
      "step": 70
    },
    {
      "epoch": 0.04352557127312296,
      "grad_norm": 0.6827275156974792,
      "learning_rate": 0.0002077054980770496,
      "loss": 0.368,
      "step": 80
    },
    {
      "epoch": 0.04896626768226333,
      "grad_norm": 1.049018383026123,
      "learning_rate": 0.00020593247807352348,
      "loss": 0.4278,
      "step": 90
    },
    {
      "epoch": 0.0544069640914037,
      "grad_norm": 1.1495347023010254,
      "learning_rate": 0.00020366772518252038,
      "loss": 0.6546,
      "step": 100
    },
    {
      "epoch": 0.0544069640914037,
      "eval_loss": 0.16608624160289764,
      "eval_runtime": 65.2368,
      "eval_samples_per_second": 5.932,
      "eval_steps_per_second": 1.487,
      "step": 100
    },
    {
      "epoch": 0.05984766050054407,
      "grad_norm": 0.08401616662740707,
      "learning_rate": 0.0002009222730524731,
      "loss": 0.1106,
      "step": 110
    },
    {
      "epoch": 0.06528835690968444,
      "grad_norm": 0.1952836960554123,
      "learning_rate": 0.00019770949725018733,
      "loss": 0.1357,
      "step": 120
    },
    {
      "epoch": 0.07072905331882481,
      "grad_norm": 0.1629328429698944,
      "learning_rate": 0.00019404505009642473,
      "loss": 0.1751,
      "step": 130
    },
    {
      "epoch": 0.07616974972796518,
      "grad_norm": 0.14246857166290283,
      "learning_rate": 0.0001899467844093695,
      "loss": 0.1564,
      "step": 140
    },
    {
      "epoch": 0.08161044613710555,
      "grad_norm": 0.45524969696998596,
      "learning_rate": 0.00018543466652749268,
      "loss": 0.2137,
      "step": 150
    },
    {
      "epoch": 0.08161044613710555,
      "eval_loss": 0.13314945995807648,
      "eval_runtime": 65.6995,
      "eval_samples_per_second": 5.89,
      "eval_steps_per_second": 1.476,
      "step": 150
    },
    {
      "epoch": 0.08705114254624592,
      "grad_norm": 0.2759036123752594,
      "learning_rate": 0.00018053067903555837,
      "loss": 0.2328,
      "step": 160
    },
    {
      "epoch": 0.09249183895538629,
      "grad_norm": 0.34225738048553467,
      "learning_rate": 0.00017525871366768012,
      "loss": 0.2684,
      "step": 170
    },
    {
      "epoch": 0.09793253536452666,
      "grad_norm": 0.5663359761238098,
      "learning_rate": 0.00016964445490919413,
      "loss": 0.3034,
      "step": 180
    },
    {
      "epoch": 0.10337323177366703,
      "grad_norm": 0.4630700945854187,
      "learning_rate": 0.00016371525486442843,
      "loss": 0.3356,
      "step": 190
    },
    {
      "epoch": 0.1088139281828074,
      "grad_norm": 1.2807186841964722,
      "learning_rate": 0.0001575,
      "loss": 0.4927,
      "step": 200
    },
    {
      "epoch": 0.1088139281828074,
      "eval_loss": 0.15209516882896423,
      "eval_runtime": 65.2491,
      "eval_samples_per_second": 5.931,
      "eval_steps_per_second": 1.487,
      "step": 200
    },
    {
      "epoch": 0.11425462459194777,
      "grad_norm": 0.1879313737154007,
      "learning_rate": 0.00015102897041285315,
      "loss": 0.1106,
      "step": 210
    },
    {
      "epoch": 0.11969532100108814,
      "grad_norm": 0.2476097196340561,
      "learning_rate": 0.00014433369230867077,
      "loss": 0.1203,
      "step": 220
    },
    {
      "epoch": 0.1251360174102285,
      "grad_norm": 0.195736363530159,
      "learning_rate": 0.0001374467844093695,
      "loss": 0.129,
      "step": 230
    },
    {
      "epoch": 0.1305767138193689,
      "grad_norm": 0.23351465165615082,
      "learning_rate": 0.0001304017990379651,
      "loss": 0.1806,
      "step": 240
    },
    {
      "epoch": 0.13601741022850924,
      "grad_norm": 0.20477648079395294,
      "learning_rate": 0.0001232330586550277,
      "loss": 0.161,
      "step": 250
    },
    {
      "epoch": 0.13601741022850924,
      "eval_loss": 0.1386343389749527,
      "eval_runtime": 65.6794,
      "eval_samples_per_second": 5.892,
      "eval_steps_per_second": 1.477,
      "step": 250
    },
    {
      "epoch": 0.14145810663764963,
      "grad_norm": 0.3020540475845337,
      "learning_rate": 0.00011597548864310363,
      "loss": 0.1828,
      "step": 260
    },
    {
      "epoch": 0.14689880304678998,
      "grad_norm": 0.5656459331512451,
      "learning_rate": 0.00010866444715376263,
      "loss": 0.211,
      "step": 270
    },
    {
      "epoch": 0.15233949945593037,
      "grad_norm": 0.6137648224830627,
      "learning_rate": 0.00010133555284623744,
      "loss": 0.2859,
      "step": 280
    },
    {
      "epoch": 0.15778019586507072,
      "grad_norm": 1.091139316558838,
      "learning_rate": 9.402451135689641e-05,
      "loss": 0.3492,
      "step": 290
    },
    {
      "epoch": 0.1632208922742111,
      "grad_norm": 0.78134685754776,
      "learning_rate": 8.676694134497232e-05,
      "loss": 0.4765,
      "step": 300
    },
    {
      "epoch": 0.1632208922742111,
      "eval_loss": 0.12224029749631882,
      "eval_runtime": 65.225,
      "eval_samples_per_second": 5.933,
      "eval_steps_per_second": 1.487,
      "step": 300
    },
    {
      "epoch": 0.16866158868335146,
      "grad_norm": 0.06177017092704773,
      "learning_rate": 7.95982009620349e-05,
      "loss": 0.0763,
      "step": 310
    },
    {
      "epoch": 0.17410228509249184,
      "grad_norm": 0.22023071348667145,
      "learning_rate": 7.255321559063053e-05,
      "loss": 0.0765,
      "step": 320
    },
    {
      "epoch": 0.1795429815016322,
      "grad_norm": 0.22449415922164917,
      "learning_rate": 6.566630769132923e-05,
      "loss": 0.1294,
      "step": 330
    },
    {
      "epoch": 0.18498367791077258,
      "grad_norm": 0.2885405719280243,
      "learning_rate": 5.897102958714686e-05,
      "loss": 0.1433,
      "step": 340
    },
    {
      "epoch": 0.19042437431991294,
      "grad_norm": 0.1774507761001587,
      "learning_rate": 5.250000000000002e-05,
      "loss": 0.1847,
      "step": 350
    },
    {
      "epoch": 0.19042437431991294,
      "eval_loss": 0.11864767968654633,
      "eval_runtime": 65.2912,
      "eval_samples_per_second": 5.927,
      "eval_steps_per_second": 1.486,
      "step": 350
    },
    {
      "epoch": 0.19586507072905332,
      "grad_norm": 0.27000942826271057,
      "learning_rate": 4.62847451355716e-05,
      "loss": 0.1948,
      "step": 360
    },
    {
      "epoch": 0.20130576713819368,
      "grad_norm": 0.3730561435222626,
      "learning_rate": 4.035554509080588e-05,
      "loss": 0.1986,
      "step": 370
    },
    {
      "epoch": 0.20674646354733406,
      "grad_norm": 0.4994836151599884,
      "learning_rate": 3.474128633231992e-05,
      "loss": 0.2262,
      "step": 380
    },
    {
      "epoch": 0.21218715995647444,
      "grad_norm": 0.7578539848327637,
      "learning_rate": 2.946932096444165e-05,
      "loss": 0.3025,
      "step": 390
    },
    {
      "epoch": 0.2176278563656148,
      "grad_norm": 1.3834261894226074,
      "learning_rate": 2.456533347250732e-05,
      "loss": 0.5652,
      "step": 400
    },
    {
      "epoch": 0.2176278563656148,
      "eval_loss": 0.1065056249499321,
      "eval_runtime": 65.2426,
      "eval_samples_per_second": 5.932,
      "eval_steps_per_second": 1.487,
      "step": 400
    },
    {
      "epoch": 0.22306855277475518,
      "grad_norm": 0.11437083035707474,
      "learning_rate": 2.005321559063053e-05,
      "loss": 0.0697,
      "step": 410
    },
    {
      "epoch": 0.22850924918389554,
      "grad_norm": 0.10665331780910492,
      "learning_rate": 1.5954949903575276e-05,
      "loss": 0.0688,
      "step": 420
    },
    {
      "epoch": 0.23394994559303592,
      "grad_norm": 0.27620697021484375,
      "learning_rate": 1.2290502749812666e-05,
      "loss": 0.1334,
      "step": 430
    },
    {
      "epoch": 0.23939064200217627,
      "grad_norm": 0.16248451173305511,
      "learning_rate": 9.077726947526898e-06,
      "loss": 0.1574,
      "step": 440
    },
    {
      "epoch": 0.24483133841131666,
      "grad_norm": 0.19599585235118866,
      "learning_rate": 6.332274817479627e-06,
      "loss": 0.1893,
      "step": 450
    },
    {
      "epoch": 0.24483133841131666,
      "eval_loss": 0.10668922960758209,
      "eval_runtime": 65.667,
      "eval_samples_per_second": 5.893,
      "eval_steps_per_second": 1.477,
      "step": 450
    },
    {
      "epoch": 0.250272034820457,
      "grad_norm": 0.19068965315818787,
      "learning_rate": 4.067521926476516e-06,
      "loss": 0.1663,
      "step": 460
    },
    {
      "epoch": 0.25571273122959737,
      "grad_norm": 0.6219221353530884,
      "learning_rate": 2.294501922950403e-06,
      "loss": 0.2751,
      "step": 470
    },
    {
      "epoch": 0.2611534276387378,
      "grad_norm": 0.6672576665878296,
      "learning_rate": 1.021852782135112e-06,
      "loss": 0.2909,
      "step": 480
    },
    {
      "epoch": 0.26659412404787813,
      "grad_norm": 0.7676600217819214,
      "learning_rate": 2.5577472271845927e-07,
      "loss": 0.3287,
      "step": 490
    },
    {
      "epoch": 0.2720348204570185,
      "grad_norm": 0.9298309683799744,
      "learning_rate": 0.0,
      "loss": 0.4581,
      "step": 500
    },
    {
      "epoch": 0.2720348204570185,
      "eval_loss": 0.10608438402414322,
      "eval_runtime": 65.7082,
      "eval_samples_per_second": 5.89,
      "eval_steps_per_second": 1.476,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 1.3049289243623424e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}