{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.31545741324921134,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006309148264984227,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.006309148264984227,
      "eval_loss": NaN,
      "eval_runtime": 14.828,
      "eval_samples_per_second": 18.006,
      "eval_steps_per_second": 2.293,
      "step": 1
    },
    {
      "epoch": 0.012618296529968454,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.01892744479495268,
      "grad_norm": NaN,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.025236593059936908,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.031545741324921134,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.03785488958990536,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.04416403785488959,
      "grad_norm": NaN,
      "learning_rate": 3.5e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.050473186119873815,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.056782334384858045,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.06309148264984227,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0694006309148265,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.07570977917981073,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.08201892744479496,
      "grad_norm": NaN,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.08832807570977919,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0946372239747634,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.10094637223974763,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.10725552050473186,
      "grad_norm": NaN,
      "learning_rate": 8.5e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.11356466876971609,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.11987381703470032,
      "grad_norm": NaN,
      "learning_rate": 9.5e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.12618296529968454,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.13249211356466878,
      "grad_norm": NaN,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.138801261829653,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.14511041009463724,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.15141955835962145,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.15772870662460567,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.15772870662460567,
      "eval_loss": NaN,
      "eval_runtime": 13.8258,
      "eval_samples_per_second": 19.312,
      "eval_steps_per_second": 2.459,
      "step": 25
    },
    {
      "epoch": 0.1640378548895899,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.17034700315457413,
      "grad_norm": NaN,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.17665615141955837,
      "grad_norm": NaN,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.1829652996845426,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.1892744479495268,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.19558359621451105,
      "grad_norm": NaN,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.20189274447949526,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.2082018927444795,
      "grad_norm": NaN,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.21451104100946372,
      "grad_norm": NaN,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.22082018927444794,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.22712933753943218,
      "grad_norm": NaN,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.2334384858044164,
      "grad_norm": NaN,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.23974763406940064,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.24605678233438485,
      "grad_norm": NaN,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.25236593059936907,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.2586750788643533,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.26498422712933756,
      "grad_norm": NaN,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.27129337539432175,
      "grad_norm": NaN,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.277602523659306,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.28391167192429023,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.2902208201892745,
      "grad_norm": NaN,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.29652996845425866,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.3028391167192429,
      "grad_norm": NaN,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.30914826498422715,
      "grad_norm": NaN,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.31545741324921134,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.31545741324921134,
      "eval_loss": NaN,
      "eval_runtime": 13.8263,
      "eval_samples_per_second": 19.311,
      "eval_steps_per_second": 2.459,
      "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": 3,
        "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": 2.61939303284736e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}