{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1830574488802337,
  "eval_steps": 500,
  "global_step": 47,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.019474196689386564,
      "grad_norm": 6.59375,
      "learning_rate": 7.916336350729292e-07,
      "loss": 1.5975836753845214,
      "step": 5
    },
    {
      "epoch": 0.03894839337877313,
      "grad_norm": 32.75,
      "learning_rate": 7.417677618185954e-07,
      "loss": 1.479573917388916,
      "step": 10
    },
    {
      "epoch": 0.05842259006815969,
      "grad_norm": 8.3125,
      "learning_rate": 6.524351777304211e-07,
      "loss": 1.3779080390930176,
      "step": 15
    },
    {
      "epoch": 0.07789678675754626,
      "grad_norm": 6.90625,
      "learning_rate": 5.339518448683944e-07,
      "loss": 1.3753812789916993,
      "step": 20
    },
    {
      "epoch": 0.09737098344693282,
      "grad_norm": 33.5,
      "learning_rate": 4e-07,
      "loss": 1.4097419738769532,
      "step": 25
    },
    {
      "epoch": 0.11684518013631938,
      "grad_norm": 13.125,
      "learning_rate": 2.6604815513160553e-07,
      "loss": 1.5697473526000976,
      "step": 30
    },
    {
      "epoch": 0.13631937682570594,
      "grad_norm": 13.1875,
      "learning_rate": 1.4756482226957898e-07,
      "loss": 1.434426975250244,
      "step": 35
    },
    {
      "epoch": 0.15579357351509251,
      "grad_norm": 14.5625,
      "learning_rate": 5.823223818140457e-08,
      "loss": 1.5301788330078125,
      "step": 40
    },
    {
      "epoch": 0.17526777020447906,
      "grad_norm": 6.0,
      "learning_rate": 8.366364927070835e-09,
      "loss": 1.5110461235046386,
      "step": 45
    },
    {
      "epoch": 0.1830574488802337,
      "step": 47,
      "total_flos": 2.2427473783689216e+16,
      "train_loss": 1.4800728635585054,
      "train_runtime": 394.9336,
      "train_samples_per_second": 0.468,
      "train_steps_per_second": 0.119
    }
  ],
  "logging_steps": 5,
  "max_steps": 47,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2427473783689216e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}