{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32,
      "grad_norm": 0.4210746958503724,
      "learning_rate": 8.202965893490877e-06,
      "loss": 0.50059814453125,
      "step": 20
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.41980726438356003,
      "learning_rate": 3.3572880904458267e-06,
      "loss": 0.4506862163543701,
      "step": 40
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.3703409945931155,
      "learning_rate": 1.0572157452321097e-07,
      "loss": 0.4307992935180664,
      "step": 60
    },
    {
      "epoch": 1.0,
      "step": 63,
      "total_flos": 6160751001600.0,
      "train_loss": 0.45696084083072724,
      "train_runtime": 420.3915,
      "train_samples_per_second": 9.515,
      "train_steps_per_second": 0.15
    }
  ],
  "logging_steps": 20,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 6160751001600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}