{
  "best_metric": 0.9554666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0554/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 31.368724822998047,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5718,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9242666666666667,
      "eval_loss": 0.26796451210975647,
      "eval_runtime": 12.4825,
      "eval_samples_per_second": 300.421,
      "eval_steps_per_second": 4.727,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.1040499210357666,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1227,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9386666666666666,
      "eval_loss": 0.2198157161474228,
      "eval_runtime": 11.8512,
      "eval_samples_per_second": 316.423,
      "eval_steps_per_second": 4.978,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9563470482826233,
      "learning_rate": 5e-05,
      "loss": 0.0506,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9466666666666667,
      "eval_loss": 0.1880520135164261,
      "eval_runtime": 12.3188,
      "eval_samples_per_second": 304.413,
      "eval_steps_per_second": 4.789,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.027465809136629105,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0152,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9514666666666667,
      "eval_loss": 0.16924162209033966,
      "eval_runtime": 12.3111,
      "eval_samples_per_second": 304.603,
      "eval_steps_per_second": 4.792,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.022229017689824104,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0045,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9546666666666667,
      "eval_loss": 0.17058934271335602,
      "eval_runtime": 12.4268,
      "eval_samples_per_second": 301.767,
      "eval_steps_per_second": 4.748,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.2985929846763611,
      "learning_rate": 0.0,
      "loss": 0.0027,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9554666666666667,
      "eval_loss": 0.1673557162284851,
      "eval_runtime": 12.4104,
      "eval_samples_per_second": 302.167,
      "eval_steps_per_second": 4.754,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}