{
  "best_metric": 0.916,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0473/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": 3.7462501525878906,
      "learning_rate": 8.400647327635769e-05,
      "loss": 0.8885,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7994666666666667,
      "eval_loss": 0.6548149585723877,
      "eval_runtime": 5.7776,
      "eval_samples_per_second": 649.063,
      "eval_steps_per_second": 10.212,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 6.762244255374248e-05,
      "loss": 0.34,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8648,
      "eval_loss": 0.4364897906780243,
      "eval_runtime": 5.7538,
      "eval_samples_per_second": 651.738,
      "eval_steps_per_second": 10.254,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.12075214833021164,
      "learning_rate": 4.5141512949348145e-05,
      "loss": 0.1545,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8813333333333333,
      "eval_loss": 0.41086047887802124,
      "eval_runtime": 5.7919,
      "eval_samples_per_second": 647.46,
      "eval_steps_per_second": 10.187,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.09474523365497589,
      "learning_rate": 2.262266506445742e-05,
      "loss": 0.0613,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8973333333333333,
      "eval_loss": 0.39339524507522583,
      "eval_runtime": 7.0468,
      "eval_samples_per_second": 532.158,
      "eval_steps_per_second": 8.373,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.001083336304873228,
      "learning_rate": 6.099806004306081e-06,
      "loss": 0.0139,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9093333333333333,
      "eval_loss": 0.3541978895664215,
      "eval_runtime": 5.8738,
      "eval_samples_per_second": 638.432,
      "eval_steps_per_second": 10.045,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.3771312236785889,
      "learning_rate": 2.2251071493339937e-10,
      "loss": 0.0048,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.916,
      "eval_loss": 0.33147773146629333,
      "eval_runtime": 5.854,
      "eval_samples_per_second": 640.587,
      "eval_steps_per_second": 10.079,
      "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
}