{
  "best_metric": 0.9266666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0801/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": 18.51688003540039,
      "learning_rate": 8.55698766265509e-05,
      "loss": 0.7705,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8298666666666666,
      "eval_loss": 0.5613557696342468,
      "eval_runtime": 11.1984,
      "eval_samples_per_second": 334.87,
      "eval_steps_per_second": 5.269,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 44.268699645996094,
      "learning_rate": 7.31517728663805e-05,
      "loss": 0.2491,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8530666666666666,
      "eval_loss": 0.5429662466049194,
      "eval_runtime": 10.8995,
      "eval_samples_per_second": 344.053,
      "eval_steps_per_second": 5.413,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.6546549797058105,
      "learning_rate": 5.5131661351986275e-05,
      "loss": 0.1283,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8754666666666666,
      "eval_loss": 0.457244336605072,
      "eval_runtime": 11.657,
      "eval_samples_per_second": 321.694,
      "eval_steps_per_second": 5.061,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.01152951829135418,
      "learning_rate": 3.5104850050159014e-05,
      "loss": 0.056,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8946666666666667,
      "eval_loss": 0.40966054797172546,
      "eval_runtime": 10.7577,
      "eval_samples_per_second": 348.589,
      "eval_steps_per_second": 5.484,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.7796046137809753,
      "learning_rate": 1.703789455194791e-05,
      "loss": 0.0156,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9221333333333334,
      "eval_loss": 0.3404841125011444,
      "eval_runtime": 10.0751,
      "eval_samples_per_second": 372.204,
      "eval_steps_per_second": 5.856,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.5587503910064697,
      "learning_rate": 4.509176970441849e-06,
      "loss": 0.002,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9266666666666666,
      "eval_loss": 0.31143733859062195,
      "eval_runtime": 9.9643,
      "eval_samples_per_second": 376.344,
      "eval_steps_per_second": 5.921,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}