{
  "best_metric": 0.4493333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0952/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": 22.55708885192871,
      "learning_rate": 0.00025030030030030026,
      "loss": 3.3487,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.21866666666666668,
      "eval_loss": 2.9076273441314697,
      "eval_runtime": 11.0135,
      "eval_samples_per_second": 340.492,
      "eval_steps_per_second": 5.357,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 23.473411560058594,
      "learning_rate": 0.0002003003003003003,
      "loss": 2.7497,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.27226666666666666,
      "eval_loss": 2.6591744422912598,
      "eval_runtime": 10.9877,
      "eval_samples_per_second": 341.291,
      "eval_steps_per_second": 5.37,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 25.809825897216797,
      "learning_rate": 0.00015030030030030027,
      "loss": 2.4617,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3410666666666667,
      "eval_loss": 2.4206814765930176,
      "eval_runtime": 11.8884,
      "eval_samples_per_second": 315.434,
      "eval_steps_per_second": 4.963,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 29.62444496154785,
      "learning_rate": 0.00010030030030030029,
      "loss": 2.1973,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.37493333333333334,
      "eval_loss": 2.250992774963379,
      "eval_runtime": 11.1603,
      "eval_samples_per_second": 336.013,
      "eval_steps_per_second": 5.287,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 29.98895263671875,
      "learning_rate": 5.0300300300300295e-05,
      "loss": 1.9477,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4176,
      "eval_loss": 2.0941033363342285,
      "eval_runtime": 11.2754,
      "eval_samples_per_second": 332.582,
      "eval_steps_per_second": 5.233,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 38.61345672607422,
      "learning_rate": 3.0030030030030027e-07,
      "loss": 1.6639,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4493333333333333,
      "eval_loss": 2.0220539569854736,
      "eval_runtime": 11.0228,
      "eval_samples_per_second": 340.203,
      "eval_steps_per_second": 5.353,
      "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
}