{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002261564012862645,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005653910032156613,
      "grad_norm": 1.1571033000946045,
      "learning_rate": 1e-05,
      "loss": 7.9905,
      "step": 1
    },
    {
      "epoch": 0.0005653910032156613,
      "eval_loss": 8.10608196258545,
      "eval_runtime": 232.686,
      "eval_samples_per_second": 12.803,
      "eval_steps_per_second": 6.403,
      "step": 1
    },
    {
      "epoch": 0.0011307820064313226,
      "grad_norm": 1.1128391027450562,
      "learning_rate": 2e-05,
      "loss": 8.0505,
      "step": 2
    },
    {
      "epoch": 0.0011307820064313226,
      "eval_loss": 8.055755615234375,
      "eval_runtime": 170.4757,
      "eval_samples_per_second": 17.475,
      "eval_steps_per_second": 8.74,
      "step": 2
    },
    {
      "epoch": 0.001696173009646984,
      "grad_norm": 1.0712642669677734,
      "learning_rate": 3e-05,
      "loss": 7.9329,
      "step": 3
    },
    {
      "epoch": 0.002261564012862645,
      "grad_norm": 1.0836079120635986,
      "learning_rate": 4e-05,
      "loss": 7.9352,
      "step": 4
    },
    {
      "epoch": 0.002261564012862645,
      "eval_loss": 8.011697769165039,
      "eval_runtime": 138.4149,
      "eval_samples_per_second": 21.522,
      "eval_steps_per_second": 10.765,
      "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": 2788217673744384.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}