{
  "best_metric": 1.6764599084854126,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.10009258564171859,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002001851712834372,
      "eval_loss": 4.284648895263672,
      "eval_runtime": 897.6878,
      "eval_samples_per_second": 9.373,
      "eval_steps_per_second": 2.344,
      "step": 1
    },
    {
      "epoch": 0.010009258564171859,
      "grad_norm": 2.063072443008423,
      "learning_rate": 0.0001015,
      "loss": 2.2796,
      "step": 50
    },
    {
      "epoch": 0.020018517128343717,
      "grad_norm": 2.084385633468628,
      "learning_rate": 0.000203,
      "loss": 1.7305,
      "step": 100
    },
    {
      "epoch": 0.030027775692515576,
      "grad_norm": 2.179790496826172,
      "learning_rate": 0.0001952737725498956,
      "loss": 1.7496,
      "step": 150
    },
    {
      "epoch": 0.040037034256687434,
      "grad_norm": 1.985134243965149,
      "learning_rate": 0.00017327133829043458,
      "loss": 1.755,
      "step": 200
    },
    {
      "epoch": 0.050046292820859296,
      "grad_norm": 1.752272605895996,
      "learning_rate": 0.00014034236838505662,
      "loss": 1.708,
      "step": 250
    },
    {
      "epoch": 0.06005555138503115,
      "grad_norm": 1.695410132408142,
      "learning_rate": 0.0001015,
      "loss": 1.6719,
      "step": 300
    },
    {
      "epoch": 0.07006480994920301,
      "grad_norm": 1.6857830286026,
      "learning_rate": 6.265763161494339e-05,
      "loss": 1.6932,
      "step": 350
    },
    {
      "epoch": 0.08007406851337487,
      "grad_norm": 1.632452368736267,
      "learning_rate": 2.972866170956543e-05,
      "loss": 1.6542,
      "step": 400
    },
    {
      "epoch": 0.09008332707754674,
      "grad_norm": 1.8353115320205688,
      "learning_rate": 7.726227450104397e-06,
      "loss": 1.653,
      "step": 450
    },
    {
      "epoch": 0.10009258564171859,
      "grad_norm": 1.4475222826004028,
      "learning_rate": 0.0,
      "loss": 1.6544,
      "step": 500
    },
    {
      "epoch": 0.10009258564171859,
      "eval_loss": 1.6764599084854126,
      "eval_runtime": 902.0997,
      "eval_samples_per_second": 9.327,
      "eval_steps_per_second": 2.332,
      "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": 7.13579154112512e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}