{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.018902698360190918,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00037805396720381833,
      "eval_loss": NaN,
      "eval_runtime": 248.662,
      "eval_samples_per_second": 8.96,
      "eval_steps_per_second": 4.48,
      "step": 1
    },
    {
      "epoch": 0.015122158688152735,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.018902698360190918,
      "eval_loss": NaN,
      "eval_runtime": 247.6685,
      "eval_samples_per_second": 8.996,
      "eval_steps_per_second": 4.498,
      "step": 50
    }
  ],
  "logging_steps": 40,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 3.2817493064024064e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}