{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 462,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21645021645021645,
      "grad_norm": 0.11153023689985275,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.379,
      "step": 100
    },
    {
      "epoch": 0.4329004329004329,
      "grad_norm": 0.2228727638721466,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.3439,
      "step": 200
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 0.3818710446357727,
      "learning_rate": 2e-05,
      "loss": 2.2485,
      "step": 300
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 0.623397946357727,
      "learning_rate": 6.3982227519528986e-06,
      "loss": 2.0799,
      "step": 400
    },
    {
      "epoch": 1.0,
      "step": 462,
      "total_flos": 8396029742284800.0,
      "train_loss": 2.2311009658879533,
      "train_runtime": 144.4923,
      "train_samples_per_second": 6.395,
      "train_steps_per_second": 3.197
    }
  ],
  "logging_steps": 100,
  "max_steps": 462,
  "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": 8396029742284800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}