{
  "best_metric": 0.348,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0163/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": 18.864070892333984,
      "learning_rate": 0.0004670935782735732,
      "loss": 3.4439,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.15333333333333332,
      "eval_loss": 3.220998525619507,
      "eval_runtime": 5.7385,
      "eval_samples_per_second": 653.481,
      "eval_steps_per_second": 10.281,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.278100967407227,
      "learning_rate": 0.00037601988894783115,
      "loss": 2.9364,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2264,
      "eval_loss": 2.8818936347961426,
      "eval_runtime": 5.7365,
      "eval_samples_per_second": 653.707,
      "eval_steps_per_second": 10.285,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.321765899658203,
      "learning_rate": 0.00025117927214825806,
      "loss": 2.7238,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.26106666666666667,
      "eval_loss": 2.7006359100341797,
      "eval_runtime": 5.6599,
      "eval_samples_per_second": 662.551,
      "eval_steps_per_second": 10.424,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 20.672670364379883,
      "learning_rate": 0.00012602267032890265,
      "loss": 2.4871,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.30533333333333335,
      "eval_loss": 2.516716241836548,
      "eval_runtime": 5.7123,
      "eval_samples_per_second": 656.479,
      "eval_steps_per_second": 10.329,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 18.137723922729492,
      "learning_rate": 3.408569387468488e-05,
      "loss": 2.2086,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.34586666666666666,
      "eval_loss": 2.4218273162841797,
      "eval_runtime": 5.9595,
      "eval_samples_per_second": 629.245,
      "eval_steps_per_second": 9.9,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 22.302570343017578,
      "learning_rate": 2.7813810714871766e-09,
      "loss": 1.9628,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.348,
      "eval_loss": 2.4226396083831787,
      "eval_runtime": 5.7705,
      "eval_samples_per_second": 649.856,
      "eval_steps_per_second": 10.224,
      "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
}