{
  "best_metric": 3.509026050567627,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.007403157446650997,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014806314893301992,
      "grad_norm": 1.0105271339416504,
      "learning_rate": 5e-05,
      "loss": 2.4248,
      "step": 1
    },
    {
      "epoch": 0.00014806314893301992,
      "eval_loss": 5.336010456085205,
      "eval_runtime": 1373.5035,
      "eval_samples_per_second": 33.127,
      "eval_steps_per_second": 4.141,
      "step": 1
    },
    {
      "epoch": 0.00029612629786603985,
      "grad_norm": 1.5958220958709717,
      "learning_rate": 0.0001,
      "loss": 3.1599,
      "step": 2
    },
    {
      "epoch": 0.0004441894467990598,
      "grad_norm": 1.818030834197998,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.6064,
      "step": 3
    },
    {
      "epoch": 0.0005922525957320797,
      "grad_norm": 2.2257354259490967,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.0994,
      "step": 4
    },
    {
      "epoch": 0.0007403157446650996,
      "grad_norm": 3.209742784500122,
      "learning_rate": 9.903926402016153e-05,
      "loss": 4.3863,
      "step": 5
    },
    {
      "epoch": 0.0008883788935981197,
      "grad_norm": 3.1330020427703857,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.0883,
      "step": 6
    },
    {
      "epoch": 0.0010364420425311395,
      "grad_norm": 2.4145240783691406,
      "learning_rate": 9.73465064747553e-05,
      "loss": 4.0968,
      "step": 7
    },
    {
      "epoch": 0.0011845051914641594,
      "grad_norm": 2.121771812438965,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.0589,
      "step": 8
    },
    {
      "epoch": 0.0013325683403971793,
      "grad_norm": 2.261179208755493,
      "learning_rate": 9.484363707663442e-05,
      "loss": 3.8118,
      "step": 9
    },
    {
      "epoch": 0.0014806314893301992,
      "grad_norm": 2.7036778926849365,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.7668,
      "step": 10
    },
    {
      "epoch": 0.0016286946382632192,
      "grad_norm": 3.0975470542907715,
      "learning_rate": 9.157348061512727e-05,
      "loss": 3.9651,
      "step": 11
    },
    {
      "epoch": 0.0017767577871962393,
      "grad_norm": 4.329109191894531,
      "learning_rate": 8.966766701456177e-05,
      "loss": 4.0882,
      "step": 12
    },
    {
      "epoch": 0.0019248209361292592,
      "grad_norm": 3.8416624069213867,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.3222,
      "step": 13
    },
    {
      "epoch": 0.002072884085062279,
      "grad_norm": 3.7130117416381836,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.8577,
      "step": 14
    },
    {
      "epoch": 0.002220947233995299,
      "grad_norm": 2.8238134384155273,
      "learning_rate": 8.296729075500344e-05,
      "loss": 3.0995,
      "step": 15
    },
    {
      "epoch": 0.0023690103829283188,
      "grad_norm": 3.1913466453552246,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.2586,
      "step": 16
    },
    {
      "epoch": 0.0025170735318613387,
      "grad_norm": 3.4828057289123535,
      "learning_rate": 7.777851165098012e-05,
      "loss": 3.5253,
      "step": 17
    },
    {
      "epoch": 0.0026651366807943586,
      "grad_norm": 2.9407994747161865,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.6475,
      "step": 18
    },
    {
      "epoch": 0.0028131998297273786,
      "grad_norm": 2.4274752140045166,
      "learning_rate": 7.211443451095007e-05,
      "loss": 3.5835,
      "step": 19
    },
    {
      "epoch": 0.0029612629786603985,
      "grad_norm": 1.6513925790786743,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.5895,
      "step": 20
    },
    {
      "epoch": 0.0031093261275934184,
      "grad_norm": 1.7945624589920044,
      "learning_rate": 6.607197326515808e-05,
      "loss": 3.611,
      "step": 21
    },
    {
      "epoch": 0.0032573892765264383,
      "grad_norm": 2.4276254177093506,
      "learning_rate": 6.294095225512603e-05,
      "loss": 3.6601,
      "step": 22
    },
    {
      "epoch": 0.0034054524254594582,
      "grad_norm": 2.5076565742492676,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 3.7379,
      "step": 23
    },
    {
      "epoch": 0.0035535155743924786,
      "grad_norm": 2.9749293327331543,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 3.6552,
      "step": 24
    },
    {
      "epoch": 0.0037015787233254985,
      "grad_norm": 3.6078078746795654,
      "learning_rate": 5.327015646150716e-05,
      "loss": 4.2382,
      "step": 25
    },
    {
      "epoch": 0.0037015787233254985,
      "eval_loss": 3.590090274810791,
      "eval_runtime": 1375.3071,
      "eval_samples_per_second": 33.084,
      "eval_steps_per_second": 4.136,
      "step": 25
    },
    {
      "epoch": 0.0038496418722585185,
      "grad_norm": 0.6510112881660461,
      "learning_rate": 5e-05,
      "loss": 1.948,
      "step": 26
    },
    {
      "epoch": 0.003997705021191538,
      "grad_norm": 0.7697362303733826,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 2.4195,
      "step": 27
    },
    {
      "epoch": 0.004145768170124558,
      "grad_norm": 0.8203458189964294,
      "learning_rate": 4.347369038899744e-05,
      "loss": 2.8089,
      "step": 28
    },
    {
      "epoch": 0.004293831319057578,
      "grad_norm": 1.0636454820632935,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 3.2538,
      "step": 29
    },
    {
      "epoch": 0.004441894467990598,
      "grad_norm": 1.189513087272644,
      "learning_rate": 3.705904774487396e-05,
      "loss": 3.5219,
      "step": 30
    },
    {
      "epoch": 0.004589957616923618,
      "grad_norm": 1.2705456018447876,
      "learning_rate": 3.392802673484193e-05,
      "loss": 3.452,
      "step": 31
    },
    {
      "epoch": 0.0047380207658566376,
      "grad_norm": 1.2574220895767212,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.4839,
      "step": 32
    },
    {
      "epoch": 0.0048860839147896575,
      "grad_norm": 1.1170214414596558,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 3.4407,
      "step": 33
    },
    {
      "epoch": 0.005034147063722677,
      "grad_norm": 1.6142178773880005,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.5797,
      "step": 34
    },
    {
      "epoch": 0.005182210212655697,
      "grad_norm": 1.546147346496582,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 3.4944,
      "step": 35
    },
    {
      "epoch": 0.005330273361588717,
      "grad_norm": 1.5059351921081543,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 3.3299,
      "step": 36
    },
    {
      "epoch": 0.005478336510521737,
      "grad_norm": 2.683159828186035,
      "learning_rate": 1.703270924499656e-05,
      "loss": 3.8225,
      "step": 37
    },
    {
      "epoch": 0.005626399659454757,
      "grad_norm": 0.6003758907318115,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.857,
      "step": 38
    },
    {
      "epoch": 0.005774462808387777,
      "grad_norm": 0.653516411781311,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 2.2992,
      "step": 39
    },
    {
      "epoch": 0.005922525957320797,
      "grad_norm": 0.7188121676445007,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 2.6286,
      "step": 40
    },
    {
      "epoch": 0.006070589106253817,
      "grad_norm": 0.7915568947792053,
      "learning_rate": 8.426519384872733e-06,
      "loss": 3.0216,
      "step": 41
    },
    {
      "epoch": 0.006218652255186837,
      "grad_norm": 0.9499257206916809,
      "learning_rate": 6.698729810778065e-06,
      "loss": 3.4042,
      "step": 42
    },
    {
      "epoch": 0.006366715404119857,
      "grad_norm": 1.0235894918441772,
      "learning_rate": 5.156362923365588e-06,
      "loss": 3.3445,
      "step": 43
    },
    {
      "epoch": 0.006514778553052877,
      "grad_norm": 1.2685362100601196,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.5116,
      "step": 44
    },
    {
      "epoch": 0.006662841701985897,
      "grad_norm": 1.3682130575180054,
      "learning_rate": 2.653493525244721e-06,
      "loss": 3.3778,
      "step": 45
    },
    {
      "epoch": 0.0068109048509189165,
      "grad_norm": 1.3854373693466187,
      "learning_rate": 1.70370868554659e-06,
      "loss": 3.5084,
      "step": 46
    },
    {
      "epoch": 0.006958967999851936,
      "grad_norm": 1.6270792484283447,
      "learning_rate": 9.607359798384785e-07,
      "loss": 3.458,
      "step": 47
    },
    {
      "epoch": 0.007107031148784957,
      "grad_norm": 1.6105763912200928,
      "learning_rate": 4.277569313094809e-07,
      "loss": 3.4925,
      "step": 48
    },
    {
      "epoch": 0.007255094297717977,
      "grad_norm": 1.7431771755218506,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 3.7432,
      "step": 49
    },
    {
      "epoch": 0.007403157446650997,
      "grad_norm": 3.2638516426086426,
      "learning_rate": 0.0,
      "loss": 4.062,
      "step": 50
    },
    {
      "epoch": 0.007403157446650997,
      "eval_loss": 3.509026050567627,
      "eval_runtime": 1374.419,
      "eval_samples_per_second": 33.105,
      "eval_steps_per_second": 4.138,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 5.968083617316864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}