{
  "best_metric": 0.392,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0793/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "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": 0.0003,
      "loss": 3.3437,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1904,
      "eval_loss": 2.955641746520996,
      "eval_runtime": 11.9974,
      "eval_samples_per_second": 312.568,
      "eval_steps_per_second": 4.918,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.908241271972656,
      "learning_rate": 0.0003,
      "loss": 2.8088,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2554666666666667,
      "eval_loss": 2.722231864929199,
      "eval_runtime": 11.7713,
      "eval_samples_per_second": 318.571,
      "eval_steps_per_second": 5.012,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 22.82229232788086,
      "learning_rate": 0.0003,
      "loss": 2.5944,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2890666666666667,
      "eval_loss": 2.6074016094207764,
      "eval_runtime": 11.4416,
      "eval_samples_per_second": 327.751,
      "eval_steps_per_second": 5.157,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 23.70648956298828,
      "learning_rate": 0.0003,
      "loss": 2.4284,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3330666666666667,
      "eval_loss": 2.4327409267425537,
      "eval_runtime": 12.3252,
      "eval_samples_per_second": 304.256,
      "eval_steps_per_second": 4.787,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 24.374858856201172,
      "learning_rate": 0.0003,
      "loss": 2.2617,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.35146666666666665,
      "eval_loss": 2.3506698608398438,
      "eval_runtime": 12.4968,
      "eval_samples_per_second": 300.078,
      "eval_steps_per_second": 4.721,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 26.081575393676758,
      "learning_rate": 0.0003,
      "loss": 2.1214,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3722666666666667,
      "eval_loss": 2.305323600769043,
      "eval_runtime": 12.1744,
      "eval_samples_per_second": 308.024,
      "eval_steps_per_second": 4.846,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 18.983413696289062,
      "learning_rate": 0.0003,
      "loss": 1.976,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.376,
      "eval_loss": 2.2121307849884033,
      "eval_runtime": 11.5741,
      "eval_samples_per_second": 324.0,
      "eval_steps_per_second": 5.098,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 1.8626,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.392,
      "eval_loss": 2.158736228942871,
      "eval_runtime": 12.4255,
      "eval_samples_per_second": 301.799,
      "eval_steps_per_second": 4.748,
      "step": 2664
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}