{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 114,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 8.119163513183594,
      "learning_rate": 1.989821441880933e-05,
      "loss": 3.3845,
      "step": 10
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 6.9536356925964355,
      "learning_rate": 1.9096319953545186e-05,
      "loss": 2.2109,
      "step": 20
    },
    {
      "epoch": 0.8,
      "grad_norm": 7.116115570068359,
      "learning_rate": 1.7557495743542586e-05,
      "loss": 1.2643,
      "step": 30
    },
    {
      "epoch": 1.0533333333333332,
      "grad_norm": 6.118326663970947,
      "learning_rate": 1.5406408174555978e-05,
      "loss": 0.7636,
      "step": 40
    },
    {
      "epoch": 1.32,
      "grad_norm": 4.654087543487549,
      "learning_rate": 1.2817325568414299e-05,
      "loss": 0.5695,
      "step": 50
    },
    {
      "epoch": 1.5866666666666667,
      "grad_norm": 6.207446575164795,
      "learning_rate": 1e-05,
      "loss": 0.4991,
      "step": 60
    },
    {
      "epoch": 1.8533333333333335,
      "grad_norm": 5.133678913116455,
      "learning_rate": 7.182674431585703e-06,
      "loss": 0.388,
      "step": 70
    },
    {
      "epoch": 2.1066666666666665,
      "grad_norm": 6.848987579345703,
      "learning_rate": 4.593591825444028e-06,
      "loss": 0.339,
      "step": 80
    },
    {
      "epoch": 2.3733333333333335,
      "grad_norm": 4.636077880859375,
      "learning_rate": 2.4425042564574186e-06,
      "loss": 0.3037,
      "step": 90
    },
    {
      "epoch": 2.64,
      "grad_norm": 6.074122428894043,
      "learning_rate": 9.036800464548157e-07,
      "loss": 0.286,
      "step": 100
    },
    {
      "epoch": 2.9066666666666667,
      "grad_norm": 5.441417217254639,
      "learning_rate": 1.0178558119067316e-07,
      "loss": 0.2766,
      "step": 110
    }
  ],
  "logging_steps": 10,
  "max_steps": 114,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2543582070374400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}