{
  "best_metric": 3.3517510890960693,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.006558237145855194,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013116474291710389,
      "eval_loss": 4.575855255126953,
      "eval_runtime": 166.0044,
      "eval_samples_per_second": 19.337,
      "eval_steps_per_second": 4.837,
      "step": 1
    },
    {
      "epoch": 0.0013116474291710388,
      "grad_norm": 3.6807003021240234,
      "learning_rate": 5.05e-06,
      "loss": 3.5819,
      "step": 10
    },
    {
      "epoch": 0.0026232948583420775,
      "grad_norm": 2.292651891708374,
      "learning_rate": 1.01e-05,
      "loss": 4.0033,
      "step": 20
    },
    {
      "epoch": 0.003934942287513116,
      "grad_norm": 3.5651023387908936,
      "learning_rate": 9.538888888888889e-06,
      "loss": 4.0922,
      "step": 30
    },
    {
      "epoch": 0.005246589716684155,
      "grad_norm": 5.502660751342773,
      "learning_rate": 8.977777777777778e-06,
      "loss": 4.2289,
      "step": 40
    },
    {
      "epoch": 0.006558237145855194,
      "grad_norm": 7.5711565017700195,
      "learning_rate": 8.416666666666667e-06,
      "loss": 4.1931,
      "step": 50
    },
    {
      "epoch": 0.006558237145855194,
      "eval_loss": 3.3517510890960693,
      "eval_runtime": 165.8751,
      "eval_samples_per_second": 19.352,
      "eval_steps_per_second": 4.841,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "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": 1.67755080794112e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}