{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008143690901687554,
  "eval_steps": 9,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.048545446319505e-05,
      "eval_loss": 2.0614755153656006,
      "eval_runtime": 1431.9492,
      "eval_samples_per_second": 12.998,
      "eval_steps_per_second": 1.625,
      "step": 1
    },
    {
      "epoch": 0.00027145636338958513,
      "grad_norm": 3.0326344966888428,
      "learning_rate": 1.5e-05,
      "loss": 1.1455,
      "step": 3
    },
    {
      "epoch": 0.0005429127267791703,
      "grad_norm": 2.6346302032470703,
      "learning_rate": 3e-05,
      "loss": 1.2541,
      "step": 6
    },
    {
      "epoch": 0.0008143690901687554,
      "grad_norm": 2.24157977104187,
      "learning_rate": 4.5e-05,
      "loss": 1.1746,
      "step": 9
    },
    {
      "epoch": 0.0008143690901687554,
      "eval_loss": 1.376136302947998,
      "eval_runtime": 1439.157,
      "eval_samples_per_second": 12.933,
      "eval_steps_per_second": 1.617,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.299769309790208e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}