{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018908059560387616,
  "eval_steps": 5,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003781611912077523,
      "grad_norm": 18.920101165771484,
      "learning_rate": 1e-05,
      "loss": 50.2344,
      "step": 1
    },
    {
      "epoch": 0.003781611912077523,
      "eval_loss": 2.642832040786743,
      "eval_runtime": 13.0225,
      "eval_samples_per_second": 34.249,
      "eval_steps_per_second": 17.124,
      "step": 1
    },
    {
      "epoch": 0.007563223824155046,
      "grad_norm": 14.773801803588867,
      "learning_rate": 2e-05,
      "loss": 43.9375,
      "step": 2
    },
    {
      "epoch": 0.011344835736232569,
      "grad_norm": 15.430819511413574,
      "learning_rate": 3e-05,
      "loss": 45.7656,
      "step": 3
    },
    {
      "epoch": 0.015126447648310093,
      "grad_norm": 12.943735122680664,
      "learning_rate": 4e-05,
      "loss": 41.0547,
      "step": 4
    },
    {
      "epoch": 0.018908059560387616,
      "grad_norm": 13.642854690551758,
      "learning_rate": 5e-05,
      "loss": 42.4766,
      "step": 5
    },
    {
      "epoch": 0.018908059560387616,
      "eval_loss": 2.632322072982788,
      "eval_runtime": 1.9759,
      "eval_samples_per_second": 225.723,
      "eval_steps_per_second": 112.862,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 42459023278080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}