{
  "best_metric": 0.9008,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0442/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 74.1542739868164,
      "learning_rate": 9.623897705919314e-05,
      "loss": 0.9625,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.784,
      "eval_loss": 0.7135282158851624,
      "eval_runtime": 6.2979,
      "eval_samples_per_second": 595.436,
      "eval_steps_per_second": 9.368,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.3379831314086914,
      "learning_rate": 8.543862808774192e-05,
      "loss": 0.3962,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8365333333333334,
      "eval_loss": 0.541252851486206,
      "eval_runtime": 6.4449,
      "eval_samples_per_second": 581.852,
      "eval_steps_per_second": 9.154,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.413537979125977,
      "learning_rate": 6.924306924189557e-05,
      "loss": 0.2267,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8392,
      "eval_loss": 0.5597156286239624,
      "eval_runtime": 6.3483,
      "eval_samples_per_second": 590.712,
      "eval_steps_per_second": 9.294,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 80.24906158447266,
      "learning_rate": 5.011792754282769e-05,
      "loss": 0.1218,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8464,
      "eval_loss": 0.5753167867660522,
      "eval_runtime": 6.2513,
      "eval_samples_per_second": 599.875,
      "eval_steps_per_second": 9.438,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.36207914352417,
      "learning_rate": 3.0974832444380136e-05,
      "loss": 0.0574,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8733333333333333,
      "eval_loss": 0.49698540568351746,
      "eval_runtime": 7.4355,
      "eval_samples_per_second": 504.334,
      "eval_steps_per_second": 7.935,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.01716252602636814,
      "learning_rate": 1.472814664270234e-05,
      "loss": 0.0228,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8853333333333333,
      "eval_loss": 0.4667545557022095,
      "eval_runtime": 6.4553,
      "eval_samples_per_second": 580.92,
      "eval_steps_per_second": 9.14,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 4.44612979888916,
      "learning_rate": 3.851280774526222e-06,
      "loss": 0.0062,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9008,
      "eval_loss": 0.4191376268863678,
      "eval_runtime": 6.4408,
      "eval_samples_per_second": 582.23,
      "eval_steps_per_second": 9.16,
      "step": 2331
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}