{
  "best_metric": 0.9072,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0340/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": 12.467190742492676,
      "learning_rate": 8.404170694504206e-05,
      "loss": 0.9258,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8013333333333333,
      "eval_loss": 0.6433719992637634,
      "eval_runtime": 6.5841,
      "eval_samples_per_second": 569.554,
      "eval_steps_per_second": 8.961,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7116051912307739,
      "learning_rate": 6.762244255374248e-05,
      "loss": 0.351,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8458666666666667,
      "eval_loss": 0.5481381416320801,
      "eval_runtime": 9.8916,
      "eval_samples_per_second": 379.108,
      "eval_steps_per_second": 5.965,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 8.932256698608398,
      "learning_rate": 4.5141512949348145e-05,
      "loss": 0.1581,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8690666666666667,
      "eval_loss": 0.47467848658561707,
      "eval_runtime": 6.5307,
      "eval_samples_per_second": 574.214,
      "eval_steps_per_second": 9.034,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.6941157579421997,
      "learning_rate": 2.262266506445742e-05,
      "loss": 0.067,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8877333333333334,
      "eval_loss": 0.4281049370765686,
      "eval_runtime": 6.3184,
      "eval_samples_per_second": 593.508,
      "eval_steps_per_second": 9.338,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5879997611045837,
      "learning_rate": 6.099806004306081e-06,
      "loss": 0.0199,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9024,
      "eval_loss": 0.38970598578453064,
      "eval_runtime": 6.3094,
      "eval_samples_per_second": 594.353,
      "eval_steps_per_second": 9.351,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.003407406620681286,
      "learning_rate": 2.2251071493339937e-10,
      "loss": 0.0058,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9072,
      "eval_loss": 0.37460559606552124,
      "eval_runtime": 6.8546,
      "eval_samples_per_second": 547.077,
      "eval_steps_per_second": 8.607,
      "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
}