{
  "best_metric": 0.99,
  "best_model_checkpoint": "gemma-finetuned-spam/run-3/checkpoint-226",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 339,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8849557522123894,
      "grad_norm": 3.5837478637695312,
      "learning_rate": 2.9543007440806287e-05,
      "loss": 0.4669,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.97,
      "eval_loss": 0.08719349652528763,
      "eval_runtime": 4.9905,
      "eval_samples_per_second": 20.038,
      "eval_steps_per_second": 10.019,
      "step": 113
    },
    {
      "epoch": 1.7699115044247788,
      "grad_norm": 0.10435254871845245,
      "learning_rate": 2.318967250729956e-05,
      "loss": 0.099,
      "step": 200
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.99,
      "eval_loss": 0.06748586893081665,
      "eval_runtime": 4.9374,
      "eval_samples_per_second": 20.253,
      "eval_steps_per_second": 10.127,
      "step": 226
    },
    {
      "epoch": 2.6548672566371683,
      "grad_norm": 0.005867947358638048,
      "learning_rate": 1.6836337573792832e-05,
      "loss": 0.0118,
      "step": 300
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.98,
      "eval_loss": 0.07953115552663803,
      "eval_runtime": 4.962,
      "eval_samples_per_second": 20.153,
      "eval_steps_per_second": 10.077,
      "step": 339
    }
  ],
  "logging_steps": 100,
  "max_steps": 565,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4773597532848128e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 3.589634237431302e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 8,
    "seed": 3
  }
}