{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.859427296392711,
  "eval_steps": 500,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.46485682409817775,
      "grad_norm": 0.7774684429168701,
      "learning_rate": 4.024960998439938e-05,
      "loss": 0.2221,
      "step": 2500
    },
    {
      "epoch": 0.9297136481963555,
      "grad_norm": 0.49191537499427795,
      "learning_rate": 2.8061622464898596e-05,
      "loss": 0.0269,
      "step": 5000
    },
    {
      "epoch": 1.3945704722945333,
      "grad_norm": 0.2874563932418823,
      "learning_rate": 1.5873634945397816e-05,
      "loss": 0.0225,
      "step": 7500
    },
    {
      "epoch": 1.859427296392711,
      "grad_norm": 0.3235009014606476,
      "learning_rate": 3.685647425897036e-06,
      "loss": 0.0205,
      "step": 10000
    }
  ],
  "logging_steps": 2500,
  "max_steps": 10756,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 2500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.857308518986547e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}