{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1428571428571428,
  "eval_steps": 5,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.6027771234512329,
      "learning_rate": 2e-05,
      "loss": 1.2426,
      "step": 1
    },
    {
      "epoch": 0.2857142857142857,
      "eval_loss": 1.0991781949996948,
      "eval_runtime": 0.804,
      "eval_samples_per_second": 2.488,
      "eval_steps_per_second": 1.244,
      "step": 1
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.7299444079399109,
      "learning_rate": 4e-05,
      "loss": 1.192,
      "step": 2
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.5905066132545471,
      "learning_rate": 6e-05,
      "loss": 1.1615,
      "step": 3
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.9356317520141602,
      "learning_rate": 8e-05,
      "loss": 1.7079,
      "step": 4
    }
  ],
  "logging_steps": 1,
  "max_steps": 4,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "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": 1528873133015040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}