{
  "best_metric": 0.4256,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0001/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": 3.2493,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.23173333333333335,
      "eval_loss": 2.81246018409729,
      "eval_runtime": 11.3214,
      "eval_samples_per_second": 331.23,
      "eval_steps_per_second": 5.211,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.766159057617188,
      "learning_rate": 0.0003,
      "loss": 2.7022,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.25893333333333335,
      "eval_loss": 2.674828290939331,
      "eval_runtime": 11.1319,
      "eval_samples_per_second": 336.869,
      "eval_steps_per_second": 5.3,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 37.188140869140625,
      "learning_rate": 0.0003,
      "loss": 2.4727,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.33866666666666667,
      "eval_loss": 2.375351905822754,
      "eval_runtime": 11.0164,
      "eval_samples_per_second": 340.403,
      "eval_steps_per_second": 5.356,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 29.748838424682617,
      "learning_rate": 0.0003,
      "loss": 2.2696,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3576,
      "eval_loss": 2.313595771789551,
      "eval_runtime": 11.492,
      "eval_samples_per_second": 326.314,
      "eval_steps_per_second": 5.134,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 23.10494041442871,
      "learning_rate": 0.0003,
      "loss": 2.1169,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.36666666666666664,
      "eval_loss": 2.2301416397094727,
      "eval_runtime": 12.2181,
      "eval_samples_per_second": 306.921,
      "eval_steps_per_second": 4.829,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 25.20330047607422,
      "learning_rate": 0.0003,
      "loss": 1.9657,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3930666666666667,
      "eval_loss": 2.1732780933380127,
      "eval_runtime": 13.0353,
      "eval_samples_per_second": 287.679,
      "eval_steps_per_second": 4.526,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 23.26473045349121,
      "learning_rate": 0.0003,
      "loss": 1.8155,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3914666666666667,
      "eval_loss": 2.1615052223205566,
      "eval_runtime": 12.18,
      "eval_samples_per_second": 307.883,
      "eval_steps_per_second": 4.844,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 1.6745,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.4256,
      "eval_loss": 2.088712453842163,
      "eval_runtime": 12.3741,
      "eval_samples_per_second": 303.053,
      "eval_steps_per_second": 4.768,
      "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
}