{
  "best_metric": 0.9330666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0247/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": 26.49774169921875,
      "learning_rate": 8.659485808097889e-05,
      "loss": 0.7506,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8570666666666666,
      "eval_loss": 0.49052831530570984,
      "eval_runtime": 8.534,
      "eval_samples_per_second": 439.417,
      "eval_steps_per_second": 6.913,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 28.803117752075195,
      "learning_rate": 7.685730736804761e-05,
      "loss": 0.2313,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.43925026059150696,
      "eval_runtime": 5.6909,
      "eval_samples_per_second": 658.942,
      "eval_steps_per_second": 10.367,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 51.373291015625,
      "learning_rate": 6.226977039554153e-05,
      "loss": 0.1218,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8874666666666666,
      "eval_loss": 0.43254029750823975,
      "eval_runtime": 6.186,
      "eval_samples_per_second": 606.21,
      "eval_steps_per_second": 9.538,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.00016223710554186255,
      "learning_rate": 4.505306743117272e-05,
      "loss": 0.0529,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9117333333333333,
      "eval_loss": 0.37938520312309265,
      "eval_runtime": 6.2698,
      "eval_samples_per_second": 598.108,
      "eval_steps_per_second": 9.41,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.003935628104954958,
      "learning_rate": 2.7828285431465317e-05,
      "loss": 0.0209,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9165333333333333,
      "eval_loss": 0.36246511340141296,
      "eval_runtime": 5.9362,
      "eval_samples_per_second": 631.718,
      "eval_steps_per_second": 9.939,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.004529351368546486,
      "learning_rate": 1.3217741312837138e-05,
      "loss": 0.0049,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9328,
      "eval_loss": 0.29801222681999207,
      "eval_runtime": 5.775,
      "eval_samples_per_second": 649.354,
      "eval_steps_per_second": 10.217,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.0077573806047439575,
      "learning_rate": 3.4457579724370674e-06,
      "loss": 0.0007,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9330666666666667,
      "eval_loss": 0.28347861766815186,
      "eval_runtime": 5.8935,
      "eval_samples_per_second": 636.298,
      "eval_steps_per_second": 10.011,
      "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
}