{
  "best_metric": 1.3836418390274048,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.19422189851905802,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0038844379703811605,
      "grad_norm": 0.17007532715797424,
      "learning_rate": 5e-05,
      "loss": 0.8051,
      "step": 1
    },
    {
      "epoch": 0.0038844379703811605,
      "eval_loss": 2.214400291442871,
      "eval_runtime": 55.3346,
      "eval_samples_per_second": 31.355,
      "eval_steps_per_second": 3.922,
      "step": 1
    },
    {
      "epoch": 0.007768875940762321,
      "grad_norm": 0.22774319350719452,
      "learning_rate": 0.0001,
      "loss": 0.964,
      "step": 2
    },
    {
      "epoch": 0.011653313911143482,
      "grad_norm": 0.2524380385875702,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.1355,
      "step": 3
    },
    {
      "epoch": 0.015537751881524642,
      "grad_norm": 0.288016140460968,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.2764,
      "step": 4
    },
    {
      "epoch": 0.019422189851905802,
      "grad_norm": 0.34158483147621155,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.4655,
      "step": 5
    },
    {
      "epoch": 0.023306627822286964,
      "grad_norm": 0.3838028311729431,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.4852,
      "step": 6
    },
    {
      "epoch": 0.027191065792668122,
      "grad_norm": 0.5480086803436279,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.8387,
      "step": 7
    },
    {
      "epoch": 0.031075503763049284,
      "grad_norm": 1.275330662727356,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.0598,
      "step": 8
    },
    {
      "epoch": 0.03495994173343044,
      "grad_norm": 0.6019589900970459,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.9839,
      "step": 9
    },
    {
      "epoch": 0.038844379703811605,
      "grad_norm": 0.16519348323345184,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.1025,
      "step": 10
    },
    {
      "epoch": 0.042728817674192766,
      "grad_norm": 0.17194363474845886,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.0485,
      "step": 11
    },
    {
      "epoch": 0.04661325564457393,
      "grad_norm": 0.2878172993659973,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.2775,
      "step": 12
    },
    {
      "epoch": 0.05049769361495508,
      "grad_norm": 0.16346238553524017,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.9148,
      "step": 13
    },
    {
      "epoch": 0.054382131585336245,
      "grad_norm": 0.16737452149391174,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.862,
      "step": 14
    },
    {
      "epoch": 0.05826656955571741,
      "grad_norm": 0.1917841136455536,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.9301,
      "step": 15
    },
    {
      "epoch": 0.06215100752609857,
      "grad_norm": 0.1946423351764679,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.015,
      "step": 16
    },
    {
      "epoch": 0.06603544549647973,
      "grad_norm": 0.19159430265426636,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.1324,
      "step": 17
    },
    {
      "epoch": 0.06991988346686089,
      "grad_norm": 0.21846984326839447,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1924,
      "step": 18
    },
    {
      "epoch": 0.07380432143724205,
      "grad_norm": 0.29288986325263977,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.2983,
      "step": 19
    },
    {
      "epoch": 0.07768875940762321,
      "grad_norm": 0.5434724688529968,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6273,
      "step": 20
    },
    {
      "epoch": 0.08157319737800436,
      "grad_norm": 2.2584354877471924,
      "learning_rate": 6.607197326515808e-05,
      "loss": 4.403,
      "step": 21
    },
    {
      "epoch": 0.08545763534838553,
      "grad_norm": 0.1508980244398117,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.0628,
      "step": 22
    },
    {
      "epoch": 0.08934207331876669,
      "grad_norm": 0.11798596382141113,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.041,
      "step": 23
    },
    {
      "epoch": 0.09322651128914786,
      "grad_norm": 0.15714554488658905,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.0616,
      "step": 24
    },
    {
      "epoch": 0.09711094925952901,
      "grad_norm": 0.2848093807697296,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.2839,
      "step": 25
    },
    {
      "epoch": 0.09711094925952901,
      "eval_loss": 1.534497618675232,
      "eval_runtime": 43.8446,
      "eval_samples_per_second": 39.572,
      "eval_steps_per_second": 4.949,
      "step": 25
    },
    {
      "epoch": 0.10099538722991017,
      "grad_norm": 0.1270134299993515,
      "learning_rate": 5e-05,
      "loss": 0.7049,
      "step": 26
    },
    {
      "epoch": 0.10487982520029134,
      "grad_norm": 0.13075926899909973,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.7464,
      "step": 27
    },
    {
      "epoch": 0.10876426317067249,
      "grad_norm": 0.15523023903369904,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.9013,
      "step": 28
    },
    {
      "epoch": 0.11264870114105366,
      "grad_norm": 0.15631172060966492,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.9871,
      "step": 29
    },
    {
      "epoch": 0.11653313911143481,
      "grad_norm": 0.17590728402137756,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.106,
      "step": 30
    },
    {
      "epoch": 0.12041757708181597,
      "grad_norm": 0.22378630936145782,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.228,
      "step": 31
    },
    {
      "epoch": 0.12430201505219714,
      "grad_norm": 0.3813501000404358,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.2546,
      "step": 32
    },
    {
      "epoch": 0.1281864530225783,
      "grad_norm": 1.0118165016174316,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 2.3369,
      "step": 33
    },
    {
      "epoch": 0.13207089099295946,
      "grad_norm": 0.38092735409736633,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.3886,
      "step": 34
    },
    {
      "epoch": 0.13595532896334062,
      "grad_norm": 0.13921162486076355,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.0392,
      "step": 35
    },
    {
      "epoch": 0.13983976693372177,
      "grad_norm": 0.10157951712608337,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.975,
      "step": 36
    },
    {
      "epoch": 0.14372420490410293,
      "grad_norm": 0.15304253995418549,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.1748,
      "step": 37
    },
    {
      "epoch": 0.1476086428744841,
      "grad_norm": 0.11945773661136627,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7164,
      "step": 38
    },
    {
      "epoch": 0.15149308084486526,
      "grad_norm": 0.11390524357557297,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.7256,
      "step": 39
    },
    {
      "epoch": 0.15537751881524642,
      "grad_norm": 0.15027418732643127,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.9102,
      "step": 40
    },
    {
      "epoch": 0.15926195678562757,
      "grad_norm": 0.14749252796173096,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.9521,
      "step": 41
    },
    {
      "epoch": 0.16314639475600873,
      "grad_norm": 0.17073273658752441,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.0067,
      "step": 42
    },
    {
      "epoch": 0.1670308327263899,
      "grad_norm": 0.19954727590084076,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.0895,
      "step": 43
    },
    {
      "epoch": 0.17091527069677107,
      "grad_norm": 0.3001015782356262,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.2653,
      "step": 44
    },
    {
      "epoch": 0.17479970866715222,
      "grad_norm": 0.6356985569000244,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.5735,
      "step": 45
    },
    {
      "epoch": 0.17868414663753338,
      "grad_norm": 3.531977653503418,
      "learning_rate": 1.70370868554659e-06,
      "loss": 5.085,
      "step": 46
    },
    {
      "epoch": 0.18256858460791453,
      "grad_norm": 0.15248890221118927,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.9541,
      "step": 47
    },
    {
      "epoch": 0.1864530225782957,
      "grad_norm": 0.10179020464420319,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.0162,
      "step": 48
    },
    {
      "epoch": 0.19033746054867687,
      "grad_norm": 0.11615335941314697,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.0128,
      "step": 49
    },
    {
      "epoch": 0.19422189851905802,
      "grad_norm": 0.2607570290565491,
      "learning_rate": 0.0,
      "loss": 1.2386,
      "step": 50
    },
    {
      "epoch": 0.19422189851905802,
      "eval_loss": 1.3836418390274048,
      "eval_runtime": 43.9694,
      "eval_samples_per_second": 39.459,
      "eval_steps_per_second": 4.935,
      "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": 2.195711408954409e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}