{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1590,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9968553459119497,
      "grad_norm": 0.6716686487197876,
      "learning_rate": 1.6012578616352204e-05,
      "loss": 0.3904,
      "step": 317
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.562258064516129,
      "eval_loss": 0.20161786675453186,
      "eval_runtime": 5.465,
      "eval_samples_per_second": 567.243,
      "eval_steps_per_second": 11.894,
      "step": 318
    },
    {
      "epoch": 1.9937106918238994,
      "grad_norm": 0.46770593523979187,
      "learning_rate": 1.2025157232704403e-05,
      "loss": 0.1712,
      "step": 634
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8016129032258065,
      "eval_loss": 0.10543324053287506,
      "eval_runtime": 5.5679,
      "eval_samples_per_second": 556.766,
      "eval_steps_per_second": 11.674,
      "step": 636
    },
    {
      "epoch": 2.990566037735849,
      "grad_norm": 0.5471485257148743,
      "learning_rate": 8.037735849056606e-06,
      "loss": 0.1139,
      "step": 951
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.853225806451613,
      "eval_loss": 0.07648013532161713,
      "eval_runtime": 5.4908,
      "eval_samples_per_second": 564.579,
      "eval_steps_per_second": 11.838,
      "step": 954
    },
    {
      "epoch": 3.9874213836477987,
      "grad_norm": 0.36325791478157043,
      "learning_rate": 4.0503144654088055e-06,
      "loss": 0.0924,
      "step": 1268
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8764516129032258,
      "eval_loss": 0.06466829031705856,
      "eval_runtime": 5.5075,
      "eval_samples_per_second": 562.869,
      "eval_steps_per_second": 11.802,
      "step": 1272
    },
    {
      "epoch": 4.984276729559748,
      "grad_norm": 0.3142065107822418,
      "learning_rate": 6.289308176100629e-08,
      "loss": 0.0835,
      "step": 1585
    }
  ],
  "logging_steps": 317,
  "max_steps": 1590,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 1000000000.0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 413495819944032.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.9663537802662723,
    "num_train_epochs": 5,
    "temperature": 16
  }
}