{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 0.8689085245132446,
      "learning_rate": 1.992708874098054e-05,
      "loss": 0.143,
      "step": 5
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.11412197351455688,
      "learning_rate": 1.7485107481711014e-05,
      "loss": 0.194,
      "step": 10
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 0.07396583259105682,
      "learning_rate": 1.2393156642875579e-05,
      "loss": 0.0887,
      "step": 15
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.029150845482945442,
      "learning_rate": 6.453951129574644e-06,
      "loss": 0.0875,
      "step": 20
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.13400128483772278,
      "learning_rate": 1.7701613410634367e-06,
      "loss": 0.0887,
      "step": 25
    },
    {
      "epoch": 1.0,
      "step": 29,
      "total_flos": 1.5530368955108557e+17,
      "train_loss": 0.11576244132272129,
      "train_runtime": 811.0761,
      "train_samples_per_second": 4.543,
      "train_steps_per_second": 0.036
    }
  ],
  "logging_steps": 5,
  "max_steps": 29,
  "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": 1.5530368955108557e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}