{
  "best_metric": 1.2975257635116577,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.034916201117318434,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006983240223463687,
      "eval_loss": 1.370945930480957,
      "eval_runtime": 52.0353,
      "eval_samples_per_second": 11.588,
      "eval_steps_per_second": 2.902,
      "step": 1
    },
    {
      "epoch": 0.006983240223463687,
      "grad_norm": 0.7985172271728516,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 1.0747,
      "step": 10
    },
    {
      "epoch": 0.013966480446927373,
      "grad_norm": 0.5064533352851868,
      "learning_rate": 8.400000000000001e-05,
      "loss": 0.9049,
      "step": 20
    },
    {
      "epoch": 0.02094972067039106,
      "grad_norm": 0.6195475459098816,
      "learning_rate": 0.000126,
      "loss": 0.9139,
      "step": 30
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 0.5974525213241577,
      "learning_rate": 0.00016800000000000002,
      "loss": 0.8777,
      "step": 40
    },
    {
      "epoch": 0.034916201117318434,
      "grad_norm": 1.1508451700210571,
      "learning_rate": 0.00021,
      "loss": 2.2731,
      "step": 50
    },
    {
      "epoch": 0.034916201117318434,
      "eval_loss": 1.2975257635116577,
      "eval_runtime": 52.0378,
      "eval_samples_per_second": 11.588,
      "eval_steps_per_second": 2.902,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "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": 1.395228272492544e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}