{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.1446540880503147,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5922580645161291,
      "eval_loss": 0.20889601111412048,
      "eval_runtime": 5.414,
      "eval_samples_per_second": 572.59,
      "eval_steps_per_second": 12.006,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.542173445224762,
      "learning_rate": 1.606918238993711e-05,
      "loss": 0.3345,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8241935483870968,
      "eval_loss": 0.10050595551729202,
      "eval_runtime": 5.7639,
      "eval_samples_per_second": 537.832,
      "eval_steps_per_second": 11.277,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8796774193548387,
      "eval_loss": 0.06686455011367798,
      "eval_runtime": 5.5547,
      "eval_samples_per_second": 558.085,
      "eval_steps_per_second": 11.702,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.4653903543949127,
      "learning_rate": 1.2138364779874214e-05,
      "loss": 0.1167,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2544,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 296976895806696.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.2538508748497722,
    "num_train_epochs": 8,
    "temperature": 8
  }
}