{
  "best_metric": 0.9282666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0826/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.021689418703317642,
      "learning_rate": 4.376876876876877e-05,
      "loss": 0.7605,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.86,
      "eval_loss": 0.4607311189174652,
      "eval_runtime": 10.611,
      "eval_samples_per_second": 353.406,
      "eval_steps_per_second": 5.56,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 52.03498840332031,
      "learning_rate": 3.7537537537537536e-05,
      "loss": 0.187,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8941333333333333,
      "eval_loss": 0.3722037374973297,
      "eval_runtime": 10.5619,
      "eval_samples_per_second": 355.051,
      "eval_steps_per_second": 5.586,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.725797653198242,
      "learning_rate": 3.128753753753754e-05,
      "loss": 0.0877,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8904,
      "eval_loss": 0.3940073549747467,
      "eval_runtime": 10.3992,
      "eval_samples_per_second": 360.604,
      "eval_steps_per_second": 5.674,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.026866769418120384,
      "learning_rate": 2.5037537537537537e-05,
      "loss": 0.0395,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9018666666666667,
      "eval_loss": 0.41048651933670044,
      "eval_runtime": 10.7235,
      "eval_samples_per_second": 349.699,
      "eval_steps_per_second": 5.502,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.013075139373540878,
      "learning_rate": 1.8787537537537537e-05,
      "loss": 0.0175,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9130666666666667,
      "eval_loss": 0.347796767950058,
      "eval_runtime": 11.5035,
      "eval_samples_per_second": 325.987,
      "eval_steps_per_second": 5.129,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.00125736219342798,
      "learning_rate": 1.2537537537537538e-05,
      "loss": 0.0046,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9226666666666666,
      "eval_loss": 0.34410667419433594,
      "eval_runtime": 10.5125,
      "eval_samples_per_second": 356.717,
      "eval_steps_per_second": 5.612,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.010775666683912277,
      "learning_rate": 6.287537537537539e-06,
      "loss": 0.0016,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9282666666666667,
      "eval_loss": 0.34793081879615784,
      "eval_runtime": 11.0411,
      "eval_samples_per_second": 339.64,
      "eval_steps_per_second": 5.344,
      "step": 2331
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}