{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.047875523638539794,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009575104727707959,
      "grad_norm": 6.70504903793335,
      "learning_rate": 1e-05,
      "loss": 9.5144,
      "step": 1
    },
    {
      "epoch": 0.009575104727707959,
      "eval_loss": 9.867530822753906,
      "eval_runtime": 17.9491,
      "eval_samples_per_second": 9.806,
      "eval_steps_per_second": 4.903,
      "step": 1
    },
    {
      "epoch": 0.019150209455415918,
      "grad_norm": 6.895511150360107,
      "learning_rate": 2e-05,
      "loss": 9.4466,
      "step": 2
    },
    {
      "epoch": 0.019150209455415918,
      "eval_loss": 9.851031303405762,
      "eval_runtime": 0.471,
      "eval_samples_per_second": 373.665,
      "eval_steps_per_second": 186.832,
      "step": 2
    },
    {
      "epoch": 0.02872531418312388,
      "grad_norm": 6.59652853012085,
      "learning_rate": 3e-05,
      "loss": 9.5581,
      "step": 3
    },
    {
      "epoch": 0.038300418910831836,
      "grad_norm": 6.697146415710449,
      "learning_rate": 4e-05,
      "loss": 9.5376,
      "step": 4
    },
    {
      "epoch": 0.038300418910831836,
      "eval_loss": 9.811354637145996,
      "eval_runtime": 0.4721,
      "eval_samples_per_second": 372.807,
      "eval_steps_per_second": 186.404,
      "step": 4
    },
    {
      "epoch": 0.047875523638539794,
      "grad_norm": 6.324582099914551,
      "learning_rate": 5e-05,
      "loss": 9.3154,
      "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": 1311170887680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}