{
  "best_metric": 2.6678664684295654,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.5959475566150179,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011918951132300357,
      "eval_loss": 4.1085944175720215,
      "eval_runtime": 13.4572,
      "eval_samples_per_second": 104.999,
      "eval_steps_per_second": 26.306,
      "step": 1
    },
    {
      "epoch": 0.05959475566150179,
      "grad_norm": 4.044219493865967,
      "learning_rate": 0.0001015,
      "loss": 3.5007,
      "step": 50
    },
    {
      "epoch": 0.11918951132300358,
      "grad_norm": 4.036204814910889,
      "learning_rate": 0.000203,
      "loss": 2.899,
      "step": 100
    },
    {
      "epoch": 0.17878426698450536,
      "grad_norm": 4.148152828216553,
      "learning_rate": 0.0001952737725498956,
      "loss": 2.8277,
      "step": 150
    },
    {
      "epoch": 0.23837902264600716,
      "grad_norm": 3.216625213623047,
      "learning_rate": 0.00017327133829043458,
      "loss": 2.7779,
      "step": 200
    },
    {
      "epoch": 0.29797377830750893,
      "grad_norm": 3.501577377319336,
      "learning_rate": 0.00014034236838505662,
      "loss": 2.7653,
      "step": 250
    },
    {
      "epoch": 0.3575685339690107,
      "grad_norm": 3.2836899757385254,
      "learning_rate": 0.0001015,
      "loss": 2.7122,
      "step": 300
    },
    {
      "epoch": 0.4171632896305125,
      "grad_norm": 4.299125671386719,
      "learning_rate": 6.265763161494339e-05,
      "loss": 2.7417,
      "step": 350
    },
    {
      "epoch": 0.4767580452920143,
      "grad_norm": 3.8667590618133545,
      "learning_rate": 2.972866170956543e-05,
      "loss": 2.6714,
      "step": 400
    },
    {
      "epoch": 0.5363528009535161,
      "grad_norm": 3.390477418899536,
      "learning_rate": 7.726227450104397e-06,
      "loss": 2.6665,
      "step": 450
    },
    {
      "epoch": 0.5959475566150179,
      "grad_norm": 3.8047099113464355,
      "learning_rate": 0.0,
      "loss": 2.6812,
      "step": 500
    },
    {
      "epoch": 0.5959475566150179,
      "eval_loss": 2.6678664684295654,
      "eval_runtime": 13.8741,
      "eval_samples_per_second": 101.844,
      "eval_steps_per_second": 25.515,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.488394911744e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}