{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007454342154304882,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007454342154304882,
      "eval_loss": 3.5522725582122803,
      "eval_runtime": 6.2707,
      "eval_samples_per_second": 90.101,
      "eval_steps_per_second": 45.13,
      "step": 1
    },
    {
      "epoch": 0.0022363026462914647,
      "grad_norm": 1.7406411170959473,
      "learning_rate": 6e-05,
      "loss": 3.4379,
      "step": 3
    },
    {
      "epoch": 0.004472605292582929,
      "grad_norm": 1.7950012683868408,
      "learning_rate": 0.00012,
      "loss": 3.4204,
      "step": 6
    },
    {
      "epoch": 0.005963473723443906,
      "eval_loss": 2.907726287841797,
      "eval_runtime": 5.4209,
      "eval_samples_per_second": 104.225,
      "eval_steps_per_second": 52.205,
      "step": 8
    },
    {
      "epoch": 0.006708907938874394,
      "grad_norm": 1.8308537006378174,
      "learning_rate": 0.00018,
      "loss": 3.0121,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 69418793041920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}