{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0027000801586297093,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006750200396574273,
      "grad_norm": 15.272266387939453,
      "learning_rate": 1e-05,
      "loss": 8.4884,
      "step": 1
    },
    {
      "epoch": 0.0006750200396574273,
      "eval_loss": NaN,
      "eval_runtime": 398.8272,
      "eval_samples_per_second": 6.256,
      "eval_steps_per_second": 3.129,
      "step": 1
    },
    {
      "epoch": 0.0013500400793148546,
      "grad_norm": 11.741817474365234,
      "learning_rate": 2e-05,
      "loss": 7.3713,
      "step": 2
    },
    {
      "epoch": 0.0013500400793148546,
      "eval_loss": NaN,
      "eval_runtime": 383.3092,
      "eval_samples_per_second": 6.509,
      "eval_steps_per_second": 3.256,
      "step": 2
    },
    {
      "epoch": 0.002025060118972282,
      "grad_norm": 12.751256942749023,
      "learning_rate": 3e-05,
      "loss": 7.9086,
      "step": 3
    },
    {
      "epoch": 0.0027000801586297093,
      "grad_norm": 11.161563873291016,
      "learning_rate": 4e-05,
      "loss": 8.2262,
      "step": 4
    },
    {
      "epoch": 0.0027000801586297093,
      "eval_loss": NaN,
      "eval_runtime": 383.4764,
      "eval_samples_per_second": 6.506,
      "eval_steps_per_second": 3.254,
      "step": 4
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4732208422060032.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}