{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006352567496029645,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006352567496029645,
      "eval_loss": 11.5,
      "eval_runtime": 23.7178,
      "eval_samples_per_second": 125.771,
      "eval_steps_per_second": 41.952,
      "step": 1
    },
    {
      "epoch": 0.0019057702488088936,
      "grad_norm": 3.185934110661037e-05,
      "learning_rate": 8.999999999999999e-05,
      "loss": 138.0,
      "step": 3
    },
    {
      "epoch": 0.0038115404976177872,
      "grad_norm": 2.9136550438124686e-05,
      "learning_rate": 0.00017999999999999998,
      "loss": 138.0,
      "step": 6
    },
    {
      "epoch": 0.005082053996823716,
      "eval_loss": 11.5,
      "eval_runtime": 23.7611,
      "eval_samples_per_second": 125.542,
      "eval_steps_per_second": 41.875,
      "step": 8
    },
    {
      "epoch": 0.005717310746426681,
      "grad_norm": 2.6557927412795834e-05,
      "learning_rate": 0.00027,
      "loss": 138.0,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3351271440384.0,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}