{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 5026,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5968961400716275,
      "grad_norm": 0.9552611708641052,
      "learning_rate": 3.895271763146266e-05,
      "loss": 1.5143,
      "step": 1500
    },
    {
      "epoch": 1.193792280143255,
      "grad_norm": 0.9094588756561279,
      "learning_rate": 2.2381794078656652e-05,
      "loss": 1.2757,
      "step": 3000
    },
    {
      "epoch": 1.7906884202148827,
      "grad_norm": 0.9588974714279175,
      "learning_rate": 5.810870525850641e-06,
      "loss": 1.206,
      "step": 4500
    }
  ],
  "logging_steps": 1500,
  "max_steps": 5026,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.86668839600128e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}