{
  "best_metric": 0.2209298312664032,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.013842746400885935,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005537098560354374,
      "grad_norm": 83.63919067382812,
      "learning_rate": 5e-05,
      "loss": 5.3284,
      "step": 1
    },
    {
      "epoch": 0.0005537098560354374,
      "eval_loss": 5.616427421569824,
      "eval_runtime": 881.9672,
      "eval_samples_per_second": 13.795,
      "eval_steps_per_second": 1.725,
      "step": 1
    },
    {
      "epoch": 0.0011074197120708748,
      "grad_norm": 81.07270812988281,
      "learning_rate": 0.0001,
      "loss": 5.0392,
      "step": 2
    },
    {
      "epoch": 0.0016611295681063123,
      "grad_norm": 77.96538543701172,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.821,
      "step": 3
    },
    {
      "epoch": 0.0022148394241417496,
      "grad_norm": 248.20559692382812,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.2793,
      "step": 4
    },
    {
      "epoch": 0.0027685492801771874,
      "grad_norm": 470.4466552734375,
      "learning_rate": 9.903926402016153e-05,
      "loss": 3.1648,
      "step": 5
    },
    {
      "epoch": 0.0033222591362126247,
      "grad_norm": 244.6553192138672,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.8212,
      "step": 6
    },
    {
      "epoch": 0.003875968992248062,
      "grad_norm": 73.94499206542969,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.1359,
      "step": 7
    },
    {
      "epoch": 0.004429678848283499,
      "grad_norm": 52.48252487182617,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.639,
      "step": 8
    },
    {
      "epoch": 0.0049833887043189366,
      "grad_norm": 42.62266159057617,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.4366,
      "step": 9
    },
    {
      "epoch": 0.005537098560354375,
      "grad_norm": 55.48554229736328,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2331,
      "step": 10
    },
    {
      "epoch": 0.006090808416389812,
      "grad_norm": 18.96228790283203,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.2517,
      "step": 11
    },
    {
      "epoch": 0.006644518272425249,
      "grad_norm": 600.3218994140625,
      "learning_rate": 8.966766701456177e-05,
      "loss": 3.1156,
      "step": 12
    },
    {
      "epoch": 0.007198228128460687,
      "grad_norm": 560.729736328125,
      "learning_rate": 8.759199037394887e-05,
      "loss": 2.4623,
      "step": 13
    },
    {
      "epoch": 0.007751937984496124,
      "grad_norm": 50.38520050048828,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.47,
      "step": 14
    },
    {
      "epoch": 0.008305647840531562,
      "grad_norm": 45.0614128112793,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.2445,
      "step": 15
    },
    {
      "epoch": 0.008859357696566999,
      "grad_norm": 16.783288955688477,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0527,
      "step": 16
    },
    {
      "epoch": 0.009413067552602437,
      "grad_norm": 401.33197021484375,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.1234,
      "step": 17
    },
    {
      "epoch": 0.009966777408637873,
      "grad_norm": 127.39128875732422,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0367,
      "step": 18
    },
    {
      "epoch": 0.010520487264673311,
      "grad_norm": 7.844943046569824,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0225,
      "step": 19
    },
    {
      "epoch": 0.01107419712070875,
      "grad_norm": 4.442848205566406,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0251,
      "step": 20
    },
    {
      "epoch": 0.011627906976744186,
      "grad_norm": 2.3369901180267334,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0091,
      "step": 21
    },
    {
      "epoch": 0.012181616832779624,
      "grad_norm": 0.6338233947753906,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0014,
      "step": 22
    },
    {
      "epoch": 0.01273532668881506,
      "grad_norm": 0.2525288164615631,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0004,
      "step": 23
    },
    {
      "epoch": 0.013289036544850499,
      "grad_norm": 202.52098083496094,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.0549,
      "step": 24
    },
    {
      "epoch": 0.013842746400885935,
      "grad_norm": 749.843017578125,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.1561,
      "step": 25
    },
    {
      "epoch": 0.013842746400885935,
      "eval_loss": 0.2209298312664032,
      "eval_runtime": 882.1499,
      "eval_samples_per_second": 13.792,
      "eval_steps_per_second": 1.724,
      "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": 1.483568811343872e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}