{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.023228803716608595,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004645760743321719,
      "grad_norm": 12.532179832458496,
      "learning_rate": 1e-05,
      "loss": 10.9676,
      "step": 1
    },
    {
      "epoch": 0.004645760743321719,
      "eval_loss": 10.539314270019531,
      "eval_runtime": 146.0906,
      "eval_samples_per_second": 2.485,
      "eval_steps_per_second": 1.246,
      "step": 1
    },
    {
      "epoch": 0.009291521486643438,
      "grad_norm": 13.664546012878418,
      "learning_rate": 2e-05,
      "loss": 10.5721,
      "step": 2
    },
    {
      "epoch": 0.009291521486643438,
      "eval_loss": 10.337026596069336,
      "eval_runtime": 14.3209,
      "eval_samples_per_second": 25.348,
      "eval_steps_per_second": 12.709,
      "step": 2
    },
    {
      "epoch": 0.013937282229965157,
      "grad_norm": 12.756531715393066,
      "learning_rate": 3e-05,
      "loss": 9.9091,
      "step": 3
    },
    {
      "epoch": 0.018583042973286876,
      "grad_norm": 13.1884183883667,
      "learning_rate": 4e-05,
      "loss": 10.6475,
      "step": 4
    },
    {
      "epoch": 0.018583042973286876,
      "eval_loss": 10.055078506469727,
      "eval_runtime": 14.2925,
      "eval_samples_per_second": 25.398,
      "eval_steps_per_second": 12.734,
      "step": 4
    },
    {
      "epoch": 0.023228803716608595,
      "grad_norm": 11.101974487304688,
      "learning_rate": 5e-05,
      "loss": 9.9337,
      "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": 281959974567936.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}