{
  "best_metric": 0.8592,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0629/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "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": 2.401801801801802e-05,
      "loss": 2.2601,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7362666666666666,
      "eval_loss": 1.1623938083648682,
      "eval_runtime": 6.8909,
      "eval_samples_per_second": 544.193,
      "eval_steps_per_second": 8.562,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.218616008758545,
      "learning_rate": 1.801801801801802e-05,
      "loss": 0.7867,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8202666666666667,
      "eval_loss": 0.6968823075294495,
      "eval_runtime": 6.7237,
      "eval_samples_per_second": 557.725,
      "eval_steps_per_second": 8.775,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 1.2036036036036036e-05,
      "loss": 0.4367,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8421333333333333,
      "eval_loss": 0.5609243512153625,
      "eval_runtime": 6.1702,
      "eval_samples_per_second": 607.755,
      "eval_steps_per_second": 9.562,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 37.256954193115234,
      "learning_rate": 6.0360360360360355e-06,
      "loss": 0.2606,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8538666666666667,
      "eval_loss": 0.5144795775413513,
      "eval_runtime": 6.6554,
      "eval_samples_per_second": 563.451,
      "eval_steps_per_second": 8.865,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 28.269798278808594,
      "learning_rate": 3.6036036036036035e-08,
      "loss": 0.1678,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8592,
      "eval_loss": 0.4866272509098053,
      "eval_runtime": 6.6464,
      "eval_samples_per_second": 564.212,
      "eval_steps_per_second": 8.877,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}