{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.45245930552482605,
      "learning_rate": 2e-05,
      "loss": 2.1483168601989746,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5142671465873718,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.2101056575775146,
      "step": 2
    },
    {
      "epoch": 1.6956521739130435,
      "grad_norm": 0.39382970333099365,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.0590713024139404,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.45731329917907715,
      "learning_rate": 1e-05,
      "loss": 2.369413137435913,
      "step": 4
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 0.3741995692253113,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.152299404144287,
      "step": 5
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.38987115025520325,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 2.0988121032714844,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 6,
  "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": 2276355718923264.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}