{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03827751196172249,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007655502392344498,
      "grad_norm": 11.79283332824707,
      "learning_rate": 1e-05,
      "loss": 7.643,
      "step": 1
    },
    {
      "epoch": 0.007655502392344498,
      "eval_loss": 8.301112174987793,
      "eval_runtime": 45.1884,
      "eval_samples_per_second": 4.869,
      "eval_steps_per_second": 2.434,
      "step": 1
    },
    {
      "epoch": 0.015311004784688996,
      "grad_norm": 12.055047035217285,
      "learning_rate": 2e-05,
      "loss": 7.6924,
      "step": 2
    },
    {
      "epoch": 0.015311004784688996,
      "eval_loss": 8.190783500671387,
      "eval_runtime": 2.7642,
      "eval_samples_per_second": 79.59,
      "eval_steps_per_second": 39.795,
      "step": 2
    },
    {
      "epoch": 0.022966507177033493,
      "grad_norm": 12.264861106872559,
      "learning_rate": 3e-05,
      "loss": 8.0242,
      "step": 3
    },
    {
      "epoch": 0.03062200956937799,
      "grad_norm": 12.398918151855469,
      "learning_rate": 4e-05,
      "loss": 7.9768,
      "step": 4
    },
    {
      "epoch": 0.03062200956937799,
      "eval_loss": 7.6074395179748535,
      "eval_runtime": 2.7728,
      "eval_samples_per_second": 79.342,
      "eval_steps_per_second": 39.671,
      "step": 4
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 12.091768264770508,
      "learning_rate": 5e-05,
      "loss": 7.2926,
      "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": 1000194661416960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}