{
  "best_metric": 0.8826666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0226/checkpoints/checkpoint-2664",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 2664,
  "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": 3e-05,
      "loss": 2.2687,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7528,
      "eval_loss": 1.0737894773483276,
      "eval_runtime": 8.9395,
      "eval_samples_per_second": 419.488,
      "eval_steps_per_second": 6.6,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.539444923400879,
      "learning_rate": 3e-05,
      "loss": 0.7139,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8264,
      "eval_loss": 0.6240754127502441,
      "eval_runtime": 7.1629,
      "eval_samples_per_second": 523.531,
      "eval_steps_per_second": 8.237,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.241427421569824,
      "learning_rate": 3e-05,
      "loss": 0.3953,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8546666666666667,
      "eval_loss": 0.4930466115474701,
      "eval_runtime": 6.9176,
      "eval_samples_per_second": 542.096,
      "eval_steps_per_second": 8.529,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.25676441192627,
      "learning_rate": 3e-05,
      "loss": 0.2536,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8594666666666667,
      "eval_loss": 0.46691587567329407,
      "eval_runtime": 6.9616,
      "eval_samples_per_second": 538.667,
      "eval_steps_per_second": 8.475,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.2814109325408936,
      "learning_rate": 3e-05,
      "loss": 0.1668,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8746666666666667,
      "eval_loss": 0.42937716841697693,
      "eval_runtime": 7.0775,
      "eval_samples_per_second": 529.847,
      "eval_steps_per_second": 8.336,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.14021453261375427,
      "learning_rate": 3e-05,
      "loss": 0.1126,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.872,
      "eval_loss": 0.46174079179763794,
      "eval_runtime": 6.9621,
      "eval_samples_per_second": 538.631,
      "eval_steps_per_second": 8.474,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.13479995727539062,
      "learning_rate": 3e-05,
      "loss": 0.0856,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8674666666666667,
      "eval_loss": 0.481466680765152,
      "eval_runtime": 6.9447,
      "eval_samples_per_second": 539.984,
      "eval_steps_per_second": 8.496,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.12986521422863007,
      "learning_rate": 3e-05,
      "loss": 0.0578,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8826666666666667,
      "eval_loss": 0.4371354877948761,
      "eval_runtime": 6.9548,
      "eval_samples_per_second": 539.199,
      "eval_steps_per_second": 8.483,
      "step": 2664
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}