{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0035866719271188266,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.173343854237653e-05,
      "grad_norm": NaN,
      "learning_rate": 1e-06,
      "loss": 0.3623,
      "step": 1
    },
    {
      "epoch": 7.173343854237653e-05,
      "eval_loss": NaN,
      "eval_runtime": 425.7627,
      "eval_samples_per_second": 13.787,
      "eval_steps_per_second": 3.448,
      "step": 1
    },
    {
      "epoch": 0.00014346687708475305,
      "grad_norm": NaN,
      "learning_rate": 2e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00021520031562712958,
      "grad_norm": NaN,
      "learning_rate": 3e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0002869337541695061,
      "grad_norm": NaN,
      "learning_rate": 4e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00035866719271188265,
      "grad_norm": NaN,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00043040063125425915,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0005021340697966357,
      "grad_norm": NaN,
      "learning_rate": 7e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0005738675083390122,
      "grad_norm": NaN,
      "learning_rate": 8e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0006456009468813888,
      "grad_norm": NaN,
      "learning_rate": 9e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0007173343854237653,
      "grad_norm": NaN,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0007890678239661418,
      "grad_norm": NaN,
      "learning_rate": 1.1e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0008608012625085183,
      "grad_norm": NaN,
      "learning_rate": 1.2e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0009325347010508949,
      "grad_norm": NaN,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0010042681395932714,
      "grad_norm": NaN,
      "learning_rate": 1.4e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.001076001578135648,
      "grad_norm": NaN,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0011477350166780244,
      "grad_norm": NaN,
      "learning_rate": 1.6e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.001219468455220401,
      "grad_norm": NaN,
      "learning_rate": 1.7e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0012912018937627776,
      "grad_norm": NaN,
      "learning_rate": 1.8e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0013629353323051541,
      "grad_norm": NaN,
      "learning_rate": 1.9e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0014346687708475306,
      "grad_norm": NaN,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.001506402209389907,
      "grad_norm": NaN,
      "learning_rate": 2.1e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0015781356479322836,
      "grad_norm": NaN,
      "learning_rate": 2.2e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.00164986908647466,
      "grad_norm": NaN,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.0017216025250170366,
      "grad_norm": NaN,
      "learning_rate": 2.4e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0017933359635594133,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0018650694021017898,
      "grad_norm": NaN,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.0019368028406441663,
      "grad_norm": NaN,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.002008536279186543,
      "grad_norm": NaN,
      "learning_rate": 2.8e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.0020802697177289193,
      "grad_norm": NaN,
      "learning_rate": 2.9e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.002152003156271296,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0022237365948136723,
      "grad_norm": NaN,
      "learning_rate": 2.9984895998119723e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.002295470033356049,
      "grad_norm": NaN,
      "learning_rate": 2.993961440992859e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.0023672034718984253,
      "grad_norm": NaN,
      "learning_rate": 2.9864246426519023e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.002438936910440802,
      "grad_norm": NaN,
      "learning_rate": 2.9758943828979444e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0025106703489831783,
      "grad_norm": NaN,
      "learning_rate": 2.9623918682727355e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0025824037875255552,
      "grad_norm": NaN,
      "learning_rate": 2.9459442910437798e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.0026541372260679317,
      "grad_norm": NaN,
      "learning_rate": 2.9265847744427305e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.0027258706646103082,
      "grad_norm": NaN,
      "learning_rate": 2.904352305959606e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.0027976041031526847,
      "grad_norm": NaN,
      "learning_rate": 2.8792916588271762e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.0028693375416950612,
      "grad_norm": NaN,
      "learning_rate": 2.8514533018536286e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0029410709802374377,
      "grad_norm": NaN,
      "learning_rate": 2.820893297785107e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.003012804418779814,
      "grad_norm": NaN,
      "learning_rate": 2.7876731904027994e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.0030845378573221907,
      "grad_norm": NaN,
      "learning_rate": 2.7518598805819542e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.003156271295864567,
      "grad_norm": NaN,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.0032280047344069437,
      "grad_norm": NaN,
      "learning_rate": 2.672747223702045e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.00329973817294932,
      "grad_norm": NaN,
      "learning_rate": 2.6296071990054167e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.0033714716114916967,
      "grad_norm": NaN,
      "learning_rate": 2.5841922957410875e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.003443205050034073,
      "grad_norm": NaN,
      "learning_rate": 2.5365939734802973e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.0035149384885764497,
      "grad_norm": NaN,
      "learning_rate": 2.4869080889095693e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.0035866719271188266,
      "grad_norm": NaN,
      "learning_rate": 2.4352347027881003e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0035866719271188266,
      "eval_loss": NaN,
      "eval_runtime": 425.4423,
      "eval_samples_per_second": 13.797,
      "eval_steps_per_second": 3.451,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": 1.6943263160205312e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}