{
  "best_metric": 1.1736711263656616,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.2841716396703609,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005683432793407218,
      "eval_loss": 1.5135992765426636,
      "eval_runtime": 20.731,
      "eval_samples_per_second": 35.744,
      "eval_steps_per_second": 8.972,
      "step": 1
    },
    {
      "epoch": 0.005683432793407218,
      "grad_norm": 0.8103986978530884,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 1.2436,
      "step": 10
    },
    {
      "epoch": 0.011366865586814436,
      "grad_norm": 0.31512126326560974,
      "learning_rate": 8.400000000000001e-05,
      "loss": 1.1831,
      "step": 20
    },
    {
      "epoch": 0.017050298380221655,
      "grad_norm": 0.5794227719306946,
      "learning_rate": 0.000126,
      "loss": 1.2505,
      "step": 30
    },
    {
      "epoch": 0.022733731173628872,
      "grad_norm": 0.6370463967323303,
      "learning_rate": 0.00016800000000000002,
      "loss": 1.2006,
      "step": 40
    },
    {
      "epoch": 0.02841716396703609,
      "grad_norm": 1.415936827659607,
      "learning_rate": 0.00021,
      "loss": 1.4222,
      "step": 50
    },
    {
      "epoch": 0.02841716396703609,
      "eval_loss": 1.355082392692566,
      "eval_runtime": 20.7459,
      "eval_samples_per_second": 35.718,
      "eval_steps_per_second": 8.966,
      "step": 50
    },
    {
      "epoch": 0.03410059676044331,
      "grad_norm": 0.22089043259620667,
      "learning_rate": 0.00020974422527728155,
      "loss": 1.2034,
      "step": 60
    },
    {
      "epoch": 0.039784029553850526,
      "grad_norm": 0.2758491635322571,
      "learning_rate": 0.0002089781472178649,
      "loss": 1.1731,
      "step": 70
    },
    {
      "epoch": 0.045467462347257744,
      "grad_norm": 0.38943949341773987,
      "learning_rate": 0.0002077054980770496,
      "loss": 1.2336,
      "step": 80
    },
    {
      "epoch": 0.05115089514066496,
      "grad_norm": 0.5280950665473938,
      "learning_rate": 0.00020593247807352348,
      "loss": 1.1845,
      "step": 90
    },
    {
      "epoch": 0.05683432793407218,
      "grad_norm": 2.150968074798584,
      "learning_rate": 0.00020366772518252038,
      "loss": 1.2446,
      "step": 100
    },
    {
      "epoch": 0.05683432793407218,
      "eval_loss": 1.2823526859283447,
      "eval_runtime": 20.8206,
      "eval_samples_per_second": 35.59,
      "eval_steps_per_second": 8.933,
      "step": 100
    },
    {
      "epoch": 0.0625177607274794,
      "grad_norm": 0.20953252911567688,
      "learning_rate": 0.0002009222730524731,
      "loss": 1.2066,
      "step": 110
    },
    {
      "epoch": 0.06820119352088662,
      "grad_norm": 0.28513628244400024,
      "learning_rate": 0.00019770949725018733,
      "loss": 1.1415,
      "step": 120
    },
    {
      "epoch": 0.07388462631429384,
      "grad_norm": 0.38282203674316406,
      "learning_rate": 0.00019404505009642473,
      "loss": 1.1126,
      "step": 130
    },
    {
      "epoch": 0.07956805910770105,
      "grad_norm": 0.6304633021354675,
      "learning_rate": 0.0001899467844093695,
      "loss": 1.1787,
      "step": 140
    },
    {
      "epoch": 0.08525149190110827,
      "grad_norm": 2.261017084121704,
      "learning_rate": 0.00018543466652749268,
      "loss": 1.1682,
      "step": 150
    },
    {
      "epoch": 0.08525149190110827,
      "eval_loss": 1.2519747018814087,
      "eval_runtime": 20.6467,
      "eval_samples_per_second": 35.89,
      "eval_steps_per_second": 9.009,
      "step": 150
    },
    {
      "epoch": 0.09093492469451549,
      "grad_norm": 0.20803095400333405,
      "learning_rate": 0.00018053067903555837,
      "loss": 1.215,
      "step": 160
    },
    {
      "epoch": 0.0966183574879227,
      "grad_norm": 0.2767871022224426,
      "learning_rate": 0.00017525871366768012,
      "loss": 1.1321,
      "step": 170
    },
    {
      "epoch": 0.10230179028132992,
      "grad_norm": 0.3595309257507324,
      "learning_rate": 0.00016964445490919413,
      "loss": 1.0872,
      "step": 180
    },
    {
      "epoch": 0.10798522307473714,
      "grad_norm": 0.4991762638092041,
      "learning_rate": 0.00016371525486442843,
      "loss": 1.1756,
      "step": 190
    },
    {
      "epoch": 0.11366865586814436,
      "grad_norm": 1.7282116413116455,
      "learning_rate": 0.0001575,
      "loss": 1.286,
      "step": 200
    },
    {
      "epoch": 0.11366865586814436,
      "eval_loss": 1.2275176048278809,
      "eval_runtime": 20.815,
      "eval_samples_per_second": 35.599,
      "eval_steps_per_second": 8.936,
      "step": 200
    },
    {
      "epoch": 0.11935208866155157,
      "grad_norm": 0.2192612886428833,
      "learning_rate": 0.00015102897041285315,
      "loss": 1.1807,
      "step": 210
    },
    {
      "epoch": 0.1250355214549588,
      "grad_norm": 0.2621805965900421,
      "learning_rate": 0.00014433369230867077,
      "loss": 1.1024,
      "step": 220
    },
    {
      "epoch": 0.13071895424836602,
      "grad_norm": 0.3690217137336731,
      "learning_rate": 0.0001374467844093695,
      "loss": 1.1082,
      "step": 230
    },
    {
      "epoch": 0.13640238704177324,
      "grad_norm": 0.713192880153656,
      "learning_rate": 0.0001304017990379651,
      "loss": 1.1818,
      "step": 240
    },
    {
      "epoch": 0.14208581983518045,
      "grad_norm": 1.5362468957901,
      "learning_rate": 0.0001232330586550277,
      "loss": 1.239,
      "step": 250
    },
    {
      "epoch": 0.14208581983518045,
      "eval_loss": 1.2070493698120117,
      "eval_runtime": 20.8556,
      "eval_samples_per_second": 35.53,
      "eval_steps_per_second": 8.918,
      "step": 250
    },
    {
      "epoch": 0.14776925262858767,
      "grad_norm": 0.2006831169128418,
      "learning_rate": 0.00011597548864310363,
      "loss": 1.1851,
      "step": 260
    },
    {
      "epoch": 0.1534526854219949,
      "grad_norm": 0.28160572052001953,
      "learning_rate": 0.00010866444715376263,
      "loss": 1.1084,
      "step": 270
    },
    {
      "epoch": 0.1591361182154021,
      "grad_norm": 0.35404494404792786,
      "learning_rate": 0.00010133555284623744,
      "loss": 1.1729,
      "step": 280
    },
    {
      "epoch": 0.16481955100880932,
      "grad_norm": 0.8237364292144775,
      "learning_rate": 9.402451135689641e-05,
      "loss": 1.1748,
      "step": 290
    },
    {
      "epoch": 0.17050298380221654,
      "grad_norm": 1.429248571395874,
      "learning_rate": 8.676694134497232e-05,
      "loss": 1.3167,
      "step": 300
    },
    {
      "epoch": 0.17050298380221654,
      "eval_loss": 1.1927704811096191,
      "eval_runtime": 20.9276,
      "eval_samples_per_second": 35.408,
      "eval_steps_per_second": 8.888,
      "step": 300
    },
    {
      "epoch": 0.17618641659562376,
      "grad_norm": 0.20985211431980133,
      "learning_rate": 7.95982009620349e-05,
      "loss": 1.1342,
      "step": 310
    },
    {
      "epoch": 0.18186984938903097,
      "grad_norm": 0.2655479609966278,
      "learning_rate": 7.255321559063053e-05,
      "loss": 1.1409,
      "step": 320
    },
    {
      "epoch": 0.1875532821824382,
      "grad_norm": 0.41280436515808105,
      "learning_rate": 6.566630769132923e-05,
      "loss": 1.1169,
      "step": 330
    },
    {
      "epoch": 0.1932367149758454,
      "grad_norm": 0.5316308736801147,
      "learning_rate": 5.897102958714686e-05,
      "loss": 1.2024,
      "step": 340
    },
    {
      "epoch": 0.19892014776925263,
      "grad_norm": 1.7537466287612915,
      "learning_rate": 5.250000000000002e-05,
      "loss": 1.2405,
      "step": 350
    },
    {
      "epoch": 0.19892014776925263,
      "eval_loss": 1.1823617219924927,
      "eval_runtime": 20.6991,
      "eval_samples_per_second": 35.799,
      "eval_steps_per_second": 8.986,
      "step": 350
    },
    {
      "epoch": 0.20460358056265984,
      "grad_norm": 0.20923574268817902,
      "learning_rate": 4.62847451355716e-05,
      "loss": 1.1516,
      "step": 360
    },
    {
      "epoch": 0.21028701335606706,
      "grad_norm": 0.2749004364013672,
      "learning_rate": 4.035554509080588e-05,
      "loss": 1.0708,
      "step": 370
    },
    {
      "epoch": 0.21597044614947428,
      "grad_norm": 0.3869272768497467,
      "learning_rate": 3.474128633231992e-05,
      "loss": 1.0946,
      "step": 380
    },
    {
      "epoch": 0.2216538789428815,
      "grad_norm": 0.6056302785873413,
      "learning_rate": 2.946932096444165e-05,
      "loss": 1.0444,
      "step": 390
    },
    {
      "epoch": 0.2273373117362887,
      "grad_norm": 1.8501702547073364,
      "learning_rate": 2.456533347250732e-05,
      "loss": 1.2803,
      "step": 400
    },
    {
      "epoch": 0.2273373117362887,
      "eval_loss": 1.1736711263656616,
      "eval_runtime": 20.689,
      "eval_samples_per_second": 35.816,
      "eval_steps_per_second": 8.99,
      "step": 400
    },
    {
      "epoch": 0.23302074452969593,
      "grad_norm": 0.20664860308170319,
      "learning_rate": 2.005321559063053e-05,
      "loss": 1.1395,
      "step": 410
    },
    {
      "epoch": 0.23870417732310314,
      "grad_norm": 0.3032397925853729,
      "learning_rate": 1.5954949903575276e-05,
      "loss": 1.0822,
      "step": 420
    },
    {
      "epoch": 0.24438761011651036,
      "grad_norm": 0.3599047064781189,
      "learning_rate": 1.2290502749812666e-05,
      "loss": 1.1818,
      "step": 430
    },
    {
      "epoch": 0.2500710429099176,
      "grad_norm": 0.6150122284889221,
      "learning_rate": 9.077726947526898e-06,
      "loss": 1.0494,
      "step": 440
    },
    {
      "epoch": 0.2557544757033248,
      "grad_norm": 1.1710139513015747,
      "learning_rate": 6.332274817479627e-06,
      "loss": 1.3281,
      "step": 450
    },
    {
      "epoch": 0.2557544757033248,
      "eval_loss": 1.1847209930419922,
      "eval_runtime": 20.8171,
      "eval_samples_per_second": 35.596,
      "eval_steps_per_second": 8.935,
      "step": 450
    },
    {
      "epoch": 0.26143790849673204,
      "grad_norm": 0.19276390969753265,
      "learning_rate": 4.067521926476516e-06,
      "loss": 1.1466,
      "step": 460
    },
    {
      "epoch": 0.26712134129013926,
      "grad_norm": 0.2616647779941559,
      "learning_rate": 2.294501922950403e-06,
      "loss": 1.1233,
      "step": 470
    },
    {
      "epoch": 0.2728047740835465,
      "grad_norm": 0.3395529091358185,
      "learning_rate": 1.021852782135112e-06,
      "loss": 1.0534,
      "step": 480
    },
    {
      "epoch": 0.2784882068769537,
      "grad_norm": 0.5176828503608704,
      "learning_rate": 2.5577472271845927e-07,
      "loss": 1.208,
      "step": 490
    },
    {
      "epoch": 0.2841716396703609,
      "grad_norm": 1.3167757987976074,
      "learning_rate": 0.0,
      "loss": 1.2601,
      "step": 500
    },
    {
      "epoch": 0.2841716396703609,
      "eval_loss": 1.180171251296997,
      "eval_runtime": 20.6202,
      "eval_samples_per_second": 35.936,
      "eval_steps_per_second": 9.02,
      "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": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4011222261170176e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}