{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0008537886872998933,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.268943436499467e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 4.268943436499467e-05,
      "eval_loss": NaN,
      "eval_runtime": 220.1114,
      "eval_samples_per_second": 44.814,
      "eval_steps_per_second": 22.407,
      "step": 1
    },
    {
      "epoch": 8.537886872998933e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.000128068303094984,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00017075773745997867,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00021344717182497332,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00021344717182497332,
      "eval_loss": NaN,
      "eval_runtime": 201.6941,
      "eval_samples_per_second": 48.906,
      "eval_steps_per_second": 24.453,
      "step": 5
    },
    {
      "epoch": 0.000256136606189968,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00029882604055496263,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00034151547491995734,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.000384204909284952,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00042689434364994664,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00042689434364994664,
      "eval_loss": NaN,
      "eval_runtime": 195.462,
      "eval_samples_per_second": 50.465,
      "eval_steps_per_second": 25.233,
      "step": 10
    },
    {
      "epoch": 0.0004695837780149413,
      "grad_norm": NaN,
      "learning_rate": 0.00019781476007338058,
      "loss": 5.9381,
      "step": 11
    },
    {
      "epoch": 0.000512273212379936,
      "grad_norm": NaN,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0005549626467449306,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0005976520811099253,
      "grad_norm": NaN,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0006403415154749199,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0006403415154749199,
      "eval_loss": NaN,
      "eval_runtime": 200.3923,
      "eval_samples_per_second": 49.223,
      "eval_steps_per_second": 24.612,
      "step": 15
    },
    {
      "epoch": 0.0006830309498399147,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0007257203842049093,
      "grad_norm": NaN,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.000768409818569904,
      "grad_norm": NaN,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0008110992529348986,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0008537886872998933,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0008537886872998933,
      "eval_loss": NaN,
      "eval_runtime": 205.8883,
      "eval_samples_per_second": 47.909,
      "eval_steps_per_second": 23.955,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 31440134209536.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}