{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01574493209998032,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003148986419996064,
      "grad_norm": 4.734130382537842,
      "learning_rate": 1e-05,
      "loss": 4.341,
      "step": 1
    },
    {
      "epoch": 0.003148986419996064,
      "eval_loss": 4.361395835876465,
      "eval_runtime": 222.7034,
      "eval_samples_per_second": 2.402,
      "eval_steps_per_second": 1.203,
      "step": 1
    },
    {
      "epoch": 0.006297972839992128,
      "grad_norm": 4.850401878356934,
      "learning_rate": 2e-05,
      "loss": 4.1851,
      "step": 2
    },
    {
      "epoch": 0.006297972839992128,
      "eval_loss": 4.306288719177246,
      "eval_runtime": 53.6766,
      "eval_samples_per_second": 9.967,
      "eval_steps_per_second": 4.993,
      "step": 2
    },
    {
      "epoch": 0.009446959259988192,
      "grad_norm": 5.053686141967773,
      "learning_rate": 3e-05,
      "loss": 4.4039,
      "step": 3
    },
    {
      "epoch": 0.012595945679984255,
      "grad_norm": 4.6040825843811035,
      "learning_rate": 4e-05,
      "loss": 4.0998,
      "step": 4
    },
    {
      "epoch": 0.012595945679984255,
      "eval_loss": 4.012307167053223,
      "eval_runtime": 55.2718,
      "eval_samples_per_second": 9.679,
      "eval_steps_per_second": 4.849,
      "step": 4
    },
    {
      "epoch": 0.01574493209998032,
      "grad_norm": 4.089077472686768,
      "learning_rate": 5e-05,
      "loss": 4.0155,
      "step": 5
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4104787234652160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}