{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.8384879725085912,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03665521191294387,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.03665521191294387,
      "eval_loss": NaN,
      "eval_runtime": 2.1884,
      "eval_samples_per_second": 22.848,
      "eval_steps_per_second": 5.941,
      "step": 1
    },
    {
      "epoch": 0.07331042382588775,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.1466208476517755,
      "grad_norm": NaN,
      "learning_rate": 9.99571699711836e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.18327605956471935,
      "grad_norm": NaN,
      "learning_rate": 9.982876141412856e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": NaN,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.2565864833906071,
      "grad_norm": NaN,
      "learning_rate": 9.931634888554937e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.293241695303551,
      "grad_norm": NaN,
      "learning_rate": 9.893332032039701e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": NaN,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.3665521191294387,
      "grad_norm": NaN,
      "learning_rate": 9.791726278367022e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.4032073310423826,
      "grad_norm": NaN,
      "learning_rate": 9.728616793536588e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.43986254295532645,
      "grad_norm": NaN,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.4765177548682703,
      "grad_norm": NaN,
      "learning_rate": 9.578385041664925e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.5131729667812142,
      "grad_norm": NaN,
      "learning_rate": 9.491548749301997e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.5498281786941581,
      "grad_norm": NaN,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.586483390607102,
      "grad_norm": NaN,
      "learning_rate": 9.295261506157986e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.6231386025200458,
      "grad_norm": NaN,
      "learning_rate": 9.186184199300464e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": NaN,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.6964490263459335,
      "grad_norm": NaN,
      "learning_rate": 8.947199994035401e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.7331042382588774,
      "grad_norm": NaN,
      "learning_rate": 8.817748015645558e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.7697594501718213,
      "grad_norm": NaN,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.8064146620847652,
      "grad_norm": NaN,
      "learning_rate": 8.540155934270471e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.843069873997709,
      "grad_norm": NaN,
      "learning_rate": 8.392544243589427e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.8797250859106529,
      "grad_norm": NaN,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.9163802978235968,
      "grad_norm": NaN,
      "learning_rate": 8.081093963579707e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.9163802978235968,
      "eval_loss": NaN,
      "eval_runtime": 2.2754,
      "eval_samples_per_second": 21.974,
      "eval_steps_per_second": 5.713,
      "step": 25
    },
    {
      "epoch": 0.9530355097365406,
      "grad_norm": NaN,
      "learning_rate": 7.917848237560709e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.9896907216494846,
      "grad_norm": NaN,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 1.0320733104238258,
      "grad_norm": NaN,
      "learning_rate": 7.577868759557654e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 1.0687285223367697,
      "grad_norm": NaN,
      "learning_rate": 7.401782177833148e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 1.1053837342497137,
      "grad_norm": NaN,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 1.1420389461626574,
      "grad_norm": NaN,
      "learning_rate": 7.03909064496551e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 1.1786941580756014,
      "grad_norm": NaN,
      "learning_rate": 6.853176097769229e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 1.2153493699885454,
      "grad_norm": NaN,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 1.252004581901489,
      "grad_norm": NaN,
      "learning_rate": 6.473978262721463e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 1.2886597938144329,
      "grad_norm": NaN,
      "learning_rate": 6.281416799501188e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 1.3253150057273768,
      "grad_norm": NaN,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 1.3619702176403208,
      "grad_norm": NaN,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 1.3986254295532645,
      "grad_norm": NaN,
      "learning_rate": 5.696287243144013e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 1.4352806414662085,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 1.4719358533791524,
      "grad_norm": NaN,
      "learning_rate": 5.303712756855988e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 1.5085910652920962,
      "grad_norm": NaN,
      "learning_rate": 5.107799157635538e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 1.54524627720504,
      "grad_norm": NaN,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 1.5819014891179841,
      "grad_norm": NaN,
      "learning_rate": 4.718583200498814e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 1.6185567010309279,
      "grad_norm": NaN,
      "learning_rate": 4.526021737278538e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 1.6552119129438716,
      "grad_norm": NaN,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 1.6918671248568156,
      "grad_norm": NaN,
      "learning_rate": 4.146823902230772e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 1.7285223367697595,
      "grad_norm": NaN,
      "learning_rate": 3.960909355034491e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 1.7651775486827033,
      "grad_norm": NaN,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 1.8018327605956472,
      "grad_norm": NaN,
      "learning_rate": 3.598217822166854e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 1.8384879725085912,
      "grad_norm": NaN,
      "learning_rate": 3.422131240442349e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 1.8384879725085912,
      "eval_loss": NaN,
      "eval_runtime": 2.2499,
      "eval_samples_per_second": 22.223,
      "eval_steps_per_second": 5.778,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.067151776504873e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}