{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.8,
      "grad_norm": 121.5,
      "learning_rate": 2.7857142857142858e-05,
      "loss": -0.4743170738220215,
      "step": 5
    },
    {
      "epoch": 3.4,
      "grad_norm": 290.0,
      "learning_rate": 2.25e-05,
      "loss": -6.682118225097656,
      "step": 10
    },
    {
      "epoch": 5.0,
      "grad_norm": 356.0,
      "learning_rate": 1.7142857142857142e-05,
      "loss": -15.288337707519531,
      "step": 15
    },
    {
      "epoch": 6.8,
      "grad_norm": 372.0,
      "learning_rate": 1.1785714285714286e-05,
      "loss": -24.783778381347656,
      "step": 20
    },
    {
      "epoch": 8.4,
      "grad_norm": 466.0,
      "learning_rate": 6.428571428571429e-06,
      "loss": -34.91150817871094,
      "step": 25
    },
    {
      "epoch": 10.0,
      "grad_norm": 484.0,
      "learning_rate": 1.0714285714285714e-06,
      "loss": -41.9350341796875,
      "step": 30
    },
    {
      "epoch": 10.0,
      "step": 30,
      "total_flos": 0.0,
      "train_loss": -20.679182291030884,
      "train_runtime": 55.8304,
      "train_samples_per_second": 7.165,
      "train_steps_per_second": 0.537
    }
  ],
  "logging_steps": 5,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}