{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.289308176100629,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5880645161290322,
      "eval_loss": 0.2025575041770935,
      "eval_runtime": 5.6953,
      "eval_samples_per_second": 544.313,
      "eval_steps_per_second": 11.413,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.5358407497406006,
      "learning_rate": 1.606918238993711e-05,
      "loss": 0.3246,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8164516129032258,
      "eval_loss": 0.09860164672136307,
      "eval_runtime": 5.572,
      "eval_samples_per_second": 556.352,
      "eval_steps_per_second": 11.665,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8767741935483871,
      "eval_loss": 0.06627923250198364,
      "eval_runtime": 5.5688,
      "eval_samples_per_second": 556.668,
      "eval_steps_per_second": 11.672,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.4557109475135803,
      "learning_rate": 1.2138364779874214e-05,
      "loss": 0.1143,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8974193548387097,
      "eval_loss": 0.05167277529835701,
      "eval_runtime": 6.0471,
      "eval_samples_per_second": 512.642,
      "eval_steps_per_second": 10.749,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.3134615421295166,
      "learning_rate": 8.207547169811321e-06,
      "loss": 0.0739,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9048387096774193,
      "eval_loss": 0.04295814409852028,
      "eval_runtime": 5.9996,
      "eval_samples_per_second": 516.701,
      "eval_steps_per_second": 10.834,
      "step": 1590
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9093548387096774,
      "eval_loss": 0.03816475719213486,
      "eval_runtime": 5.6901,
      "eval_samples_per_second": 544.807,
      "eval_steps_per_second": 11.423,
      "step": 1908
    },
    {
      "epoch": 6.289308176100629,
      "grad_norm": 0.27717915177345276,
      "learning_rate": 4.276729559748428e-06,
      "loss": 0.0591,
      "step": 2000
    }
  ],
  "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": 520991326672152.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.22380754714084072,
    "num_train_epochs": 8,
    "temperature": 10
  }
}