{
  "best_metric": 0.1689685732126236,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.4429678848283499,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008859357696566999,
      "grad_norm": 0.2614661753177643,
      "learning_rate": 5e-05,
      "loss": 0.4372,
      "step": 1
    },
    {
      "epoch": 0.008859357696566999,
      "eval_loss": 0.7574589848518372,
      "eval_runtime": 8.7536,
      "eval_samples_per_second": 86.935,
      "eval_steps_per_second": 10.967,
      "step": 1
    },
    {
      "epoch": 0.017718715393133997,
      "grad_norm": 0.3315308094024658,
      "learning_rate": 0.0001,
      "loss": 0.5025,
      "step": 2
    },
    {
      "epoch": 0.026578073089700997,
      "grad_norm": 0.34175217151641846,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.5011,
      "step": 3
    },
    {
      "epoch": 0.035437430786267994,
      "grad_norm": 0.369407057762146,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.4763,
      "step": 4
    },
    {
      "epoch": 0.044296788482835,
      "grad_norm": 0.4721171259880066,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.4941,
      "step": 5
    },
    {
      "epoch": 0.053156146179401995,
      "grad_norm": 0.40369272232055664,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.4258,
      "step": 6
    },
    {
      "epoch": 0.06201550387596899,
      "grad_norm": 0.3617587089538574,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.4032,
      "step": 7
    },
    {
      "epoch": 0.07087486157253599,
      "grad_norm": 0.3189731240272522,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.3643,
      "step": 8
    },
    {
      "epoch": 0.07973421926910298,
      "grad_norm": 0.4354797899723053,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.4005,
      "step": 9
    },
    {
      "epoch": 0.08859357696567,
      "grad_norm": 0.5214299559593201,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.3699,
      "step": 10
    },
    {
      "epoch": 0.09745293466223699,
      "grad_norm": 0.6428799033164978,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.3711,
      "step": 11
    },
    {
      "epoch": 0.10631229235880399,
      "grad_norm": 0.5861772894859314,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.3465,
      "step": 12
    },
    {
      "epoch": 0.11517165005537099,
      "grad_norm": 0.27660268545150757,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.2814,
      "step": 13
    },
    {
      "epoch": 0.12403100775193798,
      "grad_norm": 0.2138572484254837,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.2331,
      "step": 14
    },
    {
      "epoch": 0.132890365448505,
      "grad_norm": 0.23488418757915497,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.2042,
      "step": 15
    },
    {
      "epoch": 0.14174972314507198,
      "grad_norm": 0.24813207983970642,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.2283,
      "step": 16
    },
    {
      "epoch": 0.150609080841639,
      "grad_norm": 0.26133546233177185,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.2285,
      "step": 17
    },
    {
      "epoch": 0.15946843853820597,
      "grad_norm": 0.2425292283296585,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2365,
      "step": 18
    },
    {
      "epoch": 0.16832779623477298,
      "grad_norm": 0.2309657782316208,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.196,
      "step": 19
    },
    {
      "epoch": 0.17718715393134,
      "grad_norm": 0.24410651624202728,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.1919,
      "step": 20
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 0.26011574268341064,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.199,
      "step": 21
    },
    {
      "epoch": 0.19490586932447398,
      "grad_norm": 0.2311425805091858,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1844,
      "step": 22
    },
    {
      "epoch": 0.20376522702104097,
      "grad_norm": 0.2796850800514221,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.1809,
      "step": 23
    },
    {
      "epoch": 0.21262458471760798,
      "grad_norm": 0.2616519629955292,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.1608,
      "step": 24
    },
    {
      "epoch": 0.22148394241417496,
      "grad_norm": 0.8233975768089294,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.3276,
      "step": 25
    },
    {
      "epoch": 0.22148394241417496,
      "eval_loss": 0.20079676806926727,
      "eval_runtime": 8.7542,
      "eval_samples_per_second": 86.93,
      "eval_steps_per_second": 10.966,
      "step": 25
    },
    {
      "epoch": 0.23034330011074197,
      "grad_norm": 0.23005038499832153,
      "learning_rate": 5e-05,
      "loss": 0.1945,
      "step": 26
    },
    {
      "epoch": 0.23920265780730898,
      "grad_norm": 0.18238848447799683,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.1718,
      "step": 27
    },
    {
      "epoch": 0.24806201550387597,
      "grad_norm": 0.16891257464885712,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.1674,
      "step": 28
    },
    {
      "epoch": 0.25692137320044295,
      "grad_norm": 0.2011295109987259,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.1689,
      "step": 29
    },
    {
      "epoch": 0.26578073089701,
      "grad_norm": 0.175749734044075,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.1605,
      "step": 30
    },
    {
      "epoch": 0.27464008859357697,
      "grad_norm": 0.1887713372707367,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.1546,
      "step": 31
    },
    {
      "epoch": 0.28349944629014395,
      "grad_norm": 0.2062009572982788,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1687,
      "step": 32
    },
    {
      "epoch": 0.292358803986711,
      "grad_norm": 0.23018425703048706,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.1753,
      "step": 33
    },
    {
      "epoch": 0.301218161683278,
      "grad_norm": 0.21273936331272125,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1499,
      "step": 34
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 0.2382647693157196,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.1556,
      "step": 35
    },
    {
      "epoch": 0.31893687707641194,
      "grad_norm": 0.2492895871400833,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.1324,
      "step": 36
    },
    {
      "epoch": 0.327796234772979,
      "grad_norm": 0.31593284010887146,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.1734,
      "step": 37
    },
    {
      "epoch": 0.33665559246954596,
      "grad_norm": 0.1830340176820755,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1855,
      "step": 38
    },
    {
      "epoch": 0.34551495016611294,
      "grad_norm": 0.14966778457164764,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.1531,
      "step": 39
    },
    {
      "epoch": 0.35437430786268,
      "grad_norm": 0.1577373743057251,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.1528,
      "step": 40
    },
    {
      "epoch": 0.36323366555924697,
      "grad_norm": 0.1569824367761612,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.1601,
      "step": 41
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 0.16769661009311676,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1691,
      "step": 42
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.16713380813598633,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.1555,
      "step": 43
    },
    {
      "epoch": 0.38981173864894797,
      "grad_norm": 0.1945611983537674,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.151,
      "step": 44
    },
    {
      "epoch": 0.39867109634551495,
      "grad_norm": 0.17325228452682495,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.1316,
      "step": 45
    },
    {
      "epoch": 0.40753045404208194,
      "grad_norm": 0.20813417434692383,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.1633,
      "step": 46
    },
    {
      "epoch": 0.416389811738649,
      "grad_norm": 0.22054564952850342,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.1571,
      "step": 47
    },
    {
      "epoch": 0.42524916943521596,
      "grad_norm": 0.23001566529273987,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.1502,
      "step": 48
    },
    {
      "epoch": 0.43410852713178294,
      "grad_norm": 0.26263147592544556,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.1695,
      "step": 49
    },
    {
      "epoch": 0.4429678848283499,
      "grad_norm": 0.5053365230560303,
      "learning_rate": 0.0,
      "loss": 0.2582,
      "step": 50
    },
    {
      "epoch": 0.4429678848283499,
      "eval_loss": 0.1689685732126236,
      "eval_runtime": 8.753,
      "eval_samples_per_second": 86.942,
      "eval_steps_per_second": 10.968,
      "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": 1.059536353886208e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}