{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0075187969924813,
  "eval_steps": 150,
  "global_step": 67,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015037593984962405,
      "eval_loss": 0.6524645686149597,
      "eval_runtime": 2.8105,
      "eval_samples_per_second": 39.85,
      "eval_steps_per_second": 9.963,
      "step": 1
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 0.10451317578554153,
      "learning_rate": 2e-05,
      "loss": 0.5996,
      "step": 10
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.06249558925628662,
      "learning_rate": 4e-05,
      "loss": 0.6565,
      "step": 20
    },
    {
      "epoch": 0.45112781954887216,
      "grad_norm": 0.11738388985395432,
      "learning_rate": 6e-05,
      "loss": 0.5545,
      "step": 30
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 0.0771053284406662,
      "learning_rate": 8e-05,
      "loss": 0.5492,
      "step": 40
    },
    {
      "epoch": 0.7518796992481203,
      "grad_norm": 0.06850411742925644,
      "learning_rate": 0.0001,
      "loss": 0.5039,
      "step": 50
    },
    {
      "epoch": 0.9022556390977443,
      "grad_norm": 0.09918208420276642,
      "learning_rate": 3.631685049639586e-05,
      "loss": 0.4867,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 67,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 150,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7470697678831616e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}