{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0706713780918728,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014134275618374558,
      "grad_norm": 8.371660232543945,
      "learning_rate": 1e-05,
      "loss": 11.52,
      "step": 1
    },
    {
      "epoch": 0.014134275618374558,
      "eval_loss": 11.380400657653809,
      "eval_runtime": 65.2462,
      "eval_samples_per_second": 1.839,
      "eval_steps_per_second": 0.92,
      "step": 1
    },
    {
      "epoch": 0.028268551236749116,
      "grad_norm": 8.657926559448242,
      "learning_rate": 2e-05,
      "loss": 11.8081,
      "step": 2
    },
    {
      "epoch": 0.028268551236749116,
      "eval_loss": 11.175276756286621,
      "eval_runtime": 4.3283,
      "eval_samples_per_second": 27.724,
      "eval_steps_per_second": 13.862,
      "step": 2
    },
    {
      "epoch": 0.04240282685512368,
      "grad_norm": 8.969914436340332,
      "learning_rate": 3e-05,
      "loss": 11.6408,
      "step": 3
    },
    {
      "epoch": 0.05653710247349823,
      "grad_norm": 9.369935989379883,
      "learning_rate": 4e-05,
      "loss": 11.463,
      "step": 4
    },
    {
      "epoch": 0.05653710247349823,
      "eval_loss": 10.964574813842773,
      "eval_runtime": 4.41,
      "eval_samples_per_second": 27.211,
      "eval_steps_per_second": 13.605,
      "step": 4
    },
    {
      "epoch": 0.0706713780918728,
      "grad_norm": 9.48931884765625,
      "learning_rate": 5e-05,
      "loss": 11.1925,
      "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": 1371213272186880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}