{
  "best_metric": 0.9237333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0451/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": Infinity,
      "learning_rate": 9.337967438338007e-05,
      "loss": 0.8716,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8426666666666667,
      "eval_loss": 0.5280483365058899,
      "eval_runtime": 7.5436,
      "eval_samples_per_second": 497.111,
      "eval_steps_per_second": 7.821,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.467098712921143,
      "learning_rate": 7.513604728193609e-05,
      "loss": 0.2929,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8584,
      "eval_loss": 0.49429380893707275,
      "eval_runtime": 6.5722,
      "eval_samples_per_second": 570.582,
      "eval_steps_per_second": 8.977,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.449784278869629,
      "learning_rate": 5.015723661038683e-05,
      "loss": 0.1317,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8845333333333333,
      "eval_loss": 0.4138626158237457,
      "eval_runtime": 6.559,
      "eval_samples_per_second": 571.737,
      "eval_steps_per_second": 8.995,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.020251082256436348,
      "learning_rate": 2.5136294516063797e-05,
      "loss": 0.0417,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.904,
      "eval_loss": 0.38892075419425964,
      "eval_runtime": 6.5395,
      "eval_samples_per_second": 573.435,
      "eval_steps_per_second": 9.022,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.005864331033080816,
      "learning_rate": 6.777562227006756e-06,
      "loss": 0.0063,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9221333333333334,
      "eval_loss": 0.324482798576355,
      "eval_runtime": 6.9621,
      "eval_samples_per_second": 538.634,
      "eval_steps_per_second": 8.475,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.00034709961619228125,
      "learning_rate": 2.472341277037771e-10,
      "loss": 0.0007,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9237333333333333,
      "eval_loss": 0.3195088505744934,
      "eval_runtime": 7.1516,
      "eval_samples_per_second": 524.357,
      "eval_steps_per_second": 8.25,
      "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
}