{
  "best_metric": 0.8357333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0115/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": Infinity,
      "learning_rate": 2.8002157758785897e-05,
      "loss": 2.5663,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6256,
      "eval_loss": 1.5097872018814087,
      "eval_runtime": 13.6401,
      "eval_samples_per_second": 274.925,
      "eval_steps_per_second": 4.325,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 2.2540814184580827e-05,
      "loss": 1.0569,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7656,
      "eval_loss": 0.8608573079109192,
      "eval_runtime": 13.4526,
      "eval_samples_per_second": 278.758,
      "eval_steps_per_second": 4.386,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 19.23805809020996,
      "learning_rate": 1.5047170983116048e-05,
      "loss": 0.63,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8045333333333333,
      "eval_loss": 0.6690972447395325,
      "eval_runtime": 12.9082,
      "eval_samples_per_second": 290.513,
      "eval_steps_per_second": 4.571,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 7.56136021973416e-06,
      "loss": 0.4408,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8224,
      "eval_loss": 0.5882214307785034,
      "eval_runtime": 13.1176,
      "eval_samples_per_second": 285.877,
      "eval_steps_per_second": 4.498,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.733238697052002,
      "learning_rate": 2.045141632481093e-06,
      "loss": 0.3364,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8322666666666667,
      "eval_loss": 0.549090564250946,
      "eval_runtime": 13.3555,
      "eval_samples_per_second": 280.783,
      "eval_steps_per_second": 4.418,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 12.789667129516602,
      "learning_rate": 1.668828642892306e-10,
      "loss": 0.2944,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8357333333333333,
      "eval_loss": 0.5372378826141357,
      "eval_runtime": 13.5687,
      "eval_samples_per_second": 276.371,
      "eval_steps_per_second": 4.348,
      "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
}