{
  "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": 0.6776325106620789,
      "learning_rate": 1.6012578616352204e-05,
      "loss": 0.3942,
      "step": 317
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5658064516129032,
      "eval_loss": 0.20370487868785858,
      "eval_runtime": 5.4961,
      "eval_samples_per_second": 564.038,
      "eval_steps_per_second": 11.827,
      "step": 318
    },
    {
      "epoch": 1.9937106918238994,
      "grad_norm": 0.46833595633506775,
      "learning_rate": 1.2025157232704403e-05,
      "loss": 0.1728,
      "step": 634
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8029032258064516,
      "eval_loss": 0.10623838007450104,
      "eval_runtime": 5.5736,
      "eval_samples_per_second": 556.194,
      "eval_steps_per_second": 11.662,
      "step": 636
    },
    {
      "epoch": 2.990566037735849,
      "grad_norm": 0.5504111051559448,
      "learning_rate": 8.037735849056606e-06,
      "loss": 0.1147,
      "step": 951
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8551612903225806,
      "eval_loss": 0.07689892500638962,
      "eval_runtime": 5.4953,
      "eval_samples_per_second": 564.121,
      "eval_steps_per_second": 11.828,
      "step": 954
    },
    {
      "epoch": 3.9874213836477987,
      "grad_norm": 0.3658713698387146,
      "learning_rate": 4.0503144654088055e-06,
      "loss": 0.093,
      "step": 1268
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8777419354838709,
      "eval_loss": 0.06493482738733292,
      "eval_runtime": 5.4929,
      "eval_samples_per_second": 564.366,
      "eval_steps_per_second": 11.833,
      "step": 1272
    },
    {
      "epoch": 4.984276729559748,
      "grad_norm": 0.3145616352558136,
      "learning_rate": 6.289308176100629e-08,
      "loss": 0.084,
      "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": 0.024026691280687684,
    "num_train_epochs": 5,
    "temperature": 14
  }
}