{
  "best_metric": 0.8709333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0783/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": 2.2876,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7456,
      "eval_loss": 1.1184557676315308,
      "eval_runtime": 5.8777,
      "eval_samples_per_second": 638.002,
      "eval_steps_per_second": 10.038,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.7736,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8253333333333334,
      "eval_loss": 0.6526901125907898,
      "eval_runtime": 5.8673,
      "eval_samples_per_second": 639.135,
      "eval_steps_per_second": 10.056,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 12.455403327941895,
      "learning_rate": 3e-05,
      "loss": 0.4558,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.844,
      "eval_loss": 0.5330800414085388,
      "eval_runtime": 5.9485,
      "eval_samples_per_second": 630.415,
      "eval_steps_per_second": 9.919,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 50.47023010253906,
      "learning_rate": 3e-05,
      "loss": 0.2997,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8634666666666667,
      "eval_loss": 0.4764842689037323,
      "eval_runtime": 5.8966,
      "eval_samples_per_second": 635.958,
      "eval_steps_per_second": 10.006,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 21.23094940185547,
      "learning_rate": 3e-05,
      "loss": 0.2044,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8682666666666666,
      "eval_loss": 0.4480990767478943,
      "eval_runtime": 6.1942,
      "eval_samples_per_second": 605.405,
      "eval_steps_per_second": 9.525,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.4647505283355713,
      "learning_rate": 3e-05,
      "loss": 0.1467,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8706666666666667,
      "eval_loss": 0.44214603304862976,
      "eval_runtime": 5.954,
      "eval_samples_per_second": 629.832,
      "eval_steps_per_second": 9.909,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 15.504450798034668,
      "learning_rate": 3e-05,
      "loss": 0.1078,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8669333333333333,
      "eval_loss": 0.4772535264492035,
      "eval_runtime": 6.3365,
      "eval_samples_per_second": 591.814,
      "eval_steps_per_second": 9.311,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.09427732229232788,
      "learning_rate": 3e-05,
      "loss": 0.0791,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8709333333333333,
      "eval_loss": 0.4784584641456604,
      "eval_runtime": 5.8783,
      "eval_samples_per_second": 637.936,
      "eval_steps_per_second": 10.037,
      "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
}