{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.027027027027027,
  "eval_steps": 25,
  "global_step": 7,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.0,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.43243243243243246,
      "eval_loss": NaN,
      "eval_runtime": 0.202,
      "eval_samples_per_second": 79.203,
      "eval_steps_per_second": 9.9,
      "step": 1
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.0,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 0.0,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 1.7297297297297298,
      "grad_norm": 0.0,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 0.0,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 2.5945945945945947,
      "grad_norm": 0.0,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 3.027027027027027,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 7
    }
  ],
  "logging_steps": 1,
  "max_steps": 7,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 3467024302866432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}