{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 50.0,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 10.0,
      "grad_norm": 0.13918478786945343,
      "learning_rate": 2.4012e-05,
      "loss": 0.0017,
      "step": 500
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.13085678219795227,
      "learning_rate": 1.8012000000000003e-05,
      "loss": 0.0007,
      "step": 1000
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.00878223218023777,
      "learning_rate": 1.2012e-05,
      "loss": 0.0005,
      "step": 1500
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.03867659717798233,
      "learning_rate": 6.012e-06,
      "loss": 0.0004,
      "step": 2000
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.006907717324793339,
      "learning_rate": 1.2000000000000002e-08,
      "loss": 0.0003,
      "step": 2500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "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": 1.04984138843136e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}