{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.125,
      "grad_norm": 2.018779754638672,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.551,
      "step": 10
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.7354334592819214,
      "learning_rate": 0.0,
      "loss": 0.2413,
      "step": 20
    },
    {
      "epoch": 0.25,
      "step": 20,
      "total_flos": 709402781583360.0,
      "train_loss": 0.39615691900253297,
      "train_runtime": 31.3701,
      "train_samples_per_second": 10.201,
      "train_steps_per_second": 0.638
    }
  ],
  "logging_steps": 10,
  "max_steps": 20,
  "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": 709402781583360.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}