{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6968641114982579,
      "grad_norm": NaN,
      "learning_rate": 1.4700000000000001e-06,
      "loss": 50922.515,
      "step": 50
    },
    {
      "epoch": 1.3902439024390243,
      "grad_norm": NaN,
      "learning_rate": 2.9700000000000004e-06,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 2.083623693379791,
      "grad_norm": NaN,
      "learning_rate": 4.4699999999999996e-06,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 2.7804878048780486,
      "grad_norm": NaN,
      "learning_rate": 5.9700000000000004e-06,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 3.4738675958188154,
      "grad_norm": NaN,
      "learning_rate": 7.4700000000000005e-06,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 4.167247386759582,
      "grad_norm": NaN,
      "learning_rate": 8.97e-06,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 4.86411149825784,
      "grad_norm": NaN,
      "learning_rate": 1.047e-05,
      "loss": 0.0,
      "step": 350
    }
  ],
  "logging_steps": 50,
  "max_steps": 360,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2469484519424e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}