{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.716981132075472,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.0064516129032258064,
      "eval_loss": NaN,
      "eval_runtime": 5.2899,
      "eval_samples_per_second": 586.022,
      "eval_steps_per_second": 12.288,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 177614.40625,
      "learning_rate": 1.4758909853249476e-05,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.0064516129032258064,
      "eval_loss": NaN,
      "eval_runtime": 5.7027,
      "eval_samples_per_second": 543.601,
      "eval_steps_per_second": 11.398,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.0064516129032258064,
      "eval_loss": NaN,
      "eval_runtime": 5.8317,
      "eval_samples_per_second": 531.573,
      "eval_steps_per_second": 11.146,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 267733.4375,
      "learning_rate": 9.517819706498952e-06,
      "loss": 0.0,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.0064516129032258064,
      "eval_loss": NaN,
      "eval_runtime": 5.3585,
      "eval_samples_per_second": 578.521,
      "eval_steps_per_second": 12.13,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 326141.0,
      "learning_rate": 4.276729559748428e-06,
      "loss": 0.0,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1908,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 391368939443328.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9287007190664379,
    "num_train_epochs": 6,
    "temperature": 3
  }
}