{
  "best_metric": 0.20079676806926727,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.22148394241417496,
  "eval_steps": 25,
  "global_step": 25,
  "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
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.29768176943104e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}