{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04028197381671702,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008056394763343404,
      "grad_norm": 0.04025206342339516,
      "learning_rate": 1e-05,
      "loss": 10.3837,
      "step": 1
    },
    {
      "epoch": 0.008056394763343404,
      "eval_loss": 10.377728462219238,
      "eval_runtime": 20.7243,
      "eval_samples_per_second": 10.133,
      "eval_steps_per_second": 5.067,
      "step": 1
    },
    {
      "epoch": 0.016112789526686808,
      "grad_norm": 0.04140153527259827,
      "learning_rate": 2e-05,
      "loss": 10.3734,
      "step": 2
    },
    {
      "epoch": 0.016112789526686808,
      "eval_loss": 10.377717971801758,
      "eval_runtime": 0.336,
      "eval_samples_per_second": 624.978,
      "eval_steps_per_second": 312.489,
      "step": 2
    },
    {
      "epoch": 0.02416918429003021,
      "grad_norm": 0.048592984676361084,
      "learning_rate": 3e-05,
      "loss": 10.3726,
      "step": 3
    },
    {
      "epoch": 0.032225579053373615,
      "grad_norm": 0.04435373470187187,
      "learning_rate": 4e-05,
      "loss": 10.3777,
      "step": 4
    },
    {
      "epoch": 0.032225579053373615,
      "eval_loss": 10.377674102783203,
      "eval_runtime": 0.337,
      "eval_samples_per_second": 623.119,
      "eval_steps_per_second": 311.56,
      "step": 4
    },
    {
      "epoch": 0.04028197381671702,
      "grad_norm": 0.040381625294685364,
      "learning_rate": 5e-05,
      "loss": 10.3822,
      "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": 271549071360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}