{
  "best_metric": 2.4705960750579834,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.01365280906546522,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001365280906546522,
      "eval_loss": 3.064284086227417,
      "eval_runtime": 175.2575,
      "eval_samples_per_second": 35.194,
      "eval_steps_per_second": 8.798,
      "step": 1
    },
    {
      "epoch": 0.00682640453273261,
      "grad_norm": 46.66130828857422,
      "learning_rate": 0.00025,
      "loss": 8.7201,
      "step": 50
    },
    {
      "epoch": 0.01365280906546522,
      "grad_norm": 86.1082992553711,
      "learning_rate": 0.00025,
      "loss": 8.9435,
      "step": 100
    },
    {
      "epoch": 0.01365280906546522,
      "eval_loss": 2.4705960750579834,
      "eval_runtime": 175.403,
      "eval_samples_per_second": 35.165,
      "eval_steps_per_second": 8.791,
      "step": 100
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 3.53626333642752e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}