{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013634426927993182,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0034086067319982955,
      "grad_norm": 4.303162097930908,
      "learning_rate": 1e-05,
      "loss": 177.25,
      "step": 1
    },
    {
      "epoch": 0.0034086067319982955,
      "eval_loss": 11.063005447387695,
      "eval_runtime": 13.8031,
      "eval_samples_per_second": 35.861,
      "eval_steps_per_second": 17.967,
      "step": 1
    },
    {
      "epoch": 0.006817213463996591,
      "grad_norm": 5.118202209472656,
      "learning_rate": 2e-05,
      "loss": 176.875,
      "step": 2
    },
    {
      "epoch": 0.006817213463996591,
      "eval_loss": 11.063005447387695,
      "eval_runtime": 1.8321,
      "eval_samples_per_second": 270.187,
      "eval_steps_per_second": 135.366,
      "step": 2
    },
    {
      "epoch": 0.010225820195994887,
      "grad_norm": 5.093106746673584,
      "learning_rate": 3e-05,
      "loss": 177.0,
      "step": 3
    },
    {
      "epoch": 0.013634426927993182,
      "grad_norm": 4.387277126312256,
      "learning_rate": 4e-05,
      "loss": 176.9375,
      "step": 4
    },
    {
      "epoch": 0.013634426927993182,
      "eval_loss": 11.062247276306152,
      "eval_runtime": 2.1776,
      "eval_samples_per_second": 227.31,
      "eval_steps_per_second": 113.885,
      "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": 11953766400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}