{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.020335536349771224,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004067107269954245,
      "grad_norm": 0.05964348837733269,
      "learning_rate": 1e-05,
      "loss": 10.3891,
      "step": 1
    },
    {
      "epoch": 0.004067107269954245,
      "eval_loss": 10.389698028564453,
      "eval_runtime": 26.9167,
      "eval_samples_per_second": 15.418,
      "eval_steps_per_second": 7.728,
      "step": 1
    },
    {
      "epoch": 0.00813421453990849,
      "grad_norm": 0.060548555105924606,
      "learning_rate": 2e-05,
      "loss": 10.389,
      "step": 2
    },
    {
      "epoch": 0.00813421453990849,
      "eval_loss": 10.389683723449707,
      "eval_runtime": 2.3476,
      "eval_samples_per_second": 176.773,
      "eval_steps_per_second": 88.599,
      "step": 2
    },
    {
      "epoch": 0.012201321809862735,
      "grad_norm": 0.05969623476266861,
      "learning_rate": 3e-05,
      "loss": 10.3912,
      "step": 3
    },
    {
      "epoch": 0.01626842907981698,
      "grad_norm": 0.06552771478891373,
      "learning_rate": 4e-05,
      "loss": 10.3887,
      "step": 4
    },
    {
      "epoch": 0.01626842907981698,
      "eval_loss": 10.389606475830078,
      "eval_runtime": 1.7974,
      "eval_samples_per_second": 230.892,
      "eval_steps_per_second": 115.724,
      "step": 4
    },
    {
      "epoch": 0.020335536349771224,
      "grad_norm": 0.05652884021401405,
      "learning_rate": 5e-05,
      "loss": 10.3895,
      "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": 484909056000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}