{
  "best_metric": 0.3976,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0755/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": Infinity,
      "learning_rate": 0.0002576576576576576,
      "loss": 3.4364,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.18426666666666666,
      "eval_loss": 3.0445656776428223,
      "eval_runtime": 12.2342,
      "eval_samples_per_second": 306.519,
      "eval_steps_per_second": 4.823,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 29.24970817565918,
      "learning_rate": 0.0002148005148005148,
      "loss": 2.8976,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.24586666666666668,
      "eval_loss": 2.8123104572296143,
      "eval_runtime": 12.7987,
      "eval_samples_per_second": 292.998,
      "eval_steps_per_second": 4.61,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 32.70034408569336,
      "learning_rate": 0.0001719433719433719,
      "loss": 2.6495,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.2885333333333333,
      "eval_loss": 2.5953166484832764,
      "eval_runtime": 12.2288,
      "eval_samples_per_second": 306.654,
      "eval_steps_per_second": 4.825,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 26.49717903137207,
      "learning_rate": 0.00012908622908622906,
      "loss": 2.402,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3234666666666667,
      "eval_loss": 2.4826571941375732,
      "eval_runtime": 12.1826,
      "eval_samples_per_second": 307.815,
      "eval_steps_per_second": 4.843,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 39.42071533203125,
      "learning_rate": 8.622908622908623e-05,
      "loss": 2.1551,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3632,
      "eval_loss": 2.3344547748565674,
      "eval_runtime": 12.3374,
      "eval_samples_per_second": 303.954,
      "eval_steps_per_second": 4.782,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 39.25393295288086,
      "learning_rate": 4.337194337194337e-05,
      "loss": 1.8628,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3792,
      "eval_loss": 2.3014209270477295,
      "eval_runtime": 12.3112,
      "eval_samples_per_second": 304.601,
      "eval_steps_per_second": 4.792,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 25.085512161254883,
      "learning_rate": 5.148005148005147e-07,
      "loss": 1.4977,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3976,
      "eval_loss": 2.3454506397247314,
      "eval_runtime": 12.4051,
      "eval_samples_per_second": 302.295,
      "eval_steps_per_second": 4.756,
      "step": 2331
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}