{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004876116173467833,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012190290433669582,
      "grad_norm": 12.580065727233887,
      "learning_rate": 1e-05,
      "loss": 7.7986,
      "step": 1
    },
    {
      "epoch": 0.00012190290433669582,
      "eval_loss": 8.015130043029785,
      "eval_runtime": 976.1984,
      "eval_samples_per_second": 14.153,
      "eval_steps_per_second": 7.076,
      "step": 1
    },
    {
      "epoch": 0.00024380580867339164,
      "grad_norm": 12.032500267028809,
      "learning_rate": 2e-05,
      "loss": 8.6883,
      "step": 2
    },
    {
      "epoch": 0.00024380580867339164,
      "eval_loss": 7.6427741050720215,
      "eval_runtime": 1074.3538,
      "eval_samples_per_second": 12.86,
      "eval_steps_per_second": 6.43,
      "step": 2
    },
    {
      "epoch": 0.00036570871301008746,
      "grad_norm": 15.266983032226562,
      "learning_rate": 3e-05,
      "loss": 7.0839,
      "step": 3
    },
    {
      "epoch": 0.0004876116173467833,
      "grad_norm": 13.781106948852539,
      "learning_rate": 4e-05,
      "loss": 7.7534,
      "step": 4
    },
    {
      "epoch": 0.0004876116173467833,
      "eval_loss": 7.029819488525391,
      "eval_runtime": 792.9246,
      "eval_samples_per_second": 17.424,
      "eval_steps_per_second": 8.712,
      "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": 3884084921106432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}