{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 54,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 3.783726930618286,
      "learning_rate": 4.166666666666667e-05,
      "loss": 2.2442,
      "step": 10
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 2.9478728771209717,
      "learning_rate": 3.240740740740741e-05,
      "loss": 1.8694,
      "step": 20
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 2.7791972160339355,
      "learning_rate": 2.314814814814815e-05,
      "loss": 1.3715,
      "step": 30
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 2.7697410583496094,
      "learning_rate": 1.388888888888889e-05,
      "loss": 1.1962,
      "step": 40
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 2.187772035598755,
      "learning_rate": 4.6296296296296296e-06,
      "loss": 1.0249,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 54,
  "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": 202977460224000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}