{
  "best_metric": 0.5122666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0279/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": 0.0004850126564054637,
      "loss": 3.4264,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.17946666666666666,
      "eval_loss": 3.109565258026123,
      "eval_runtime": 11.2959,
      "eval_samples_per_second": 331.98,
      "eval_steps_per_second": 5.223,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00044184758936602033,
      "loss": 2.9334,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.24773333333333333,
      "eval_loss": 2.7965776920318604,
      "eval_runtime": 12.0353,
      "eval_samples_per_second": 311.583,
      "eval_steps_per_second": 4.902,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00037568023640968044,
      "loss": 2.592,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3272,
      "eval_loss": 2.5242860317230225,
      "eval_runtime": 11.3739,
      "eval_samples_per_second": 329.703,
      "eval_steps_per_second": 5.187,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 4.505033016204834,
      "learning_rate": 0.00029418606892278544,
      "loss": 2.2892,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.36746666666666666,
      "eval_loss": 2.306777000427246,
      "eval_runtime": 11.2756,
      "eval_samples_per_second": 332.577,
      "eval_steps_per_second": 5.233,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 15.623068809509277,
      "learning_rate": 0.0002073624094068776,
      "loss": 1.9815,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.42213333333333336,
      "eval_loss": 2.084101676940918,
      "eval_runtime": 11.8803,
      "eval_samples_per_second": 315.649,
      "eval_steps_per_second": 4.966,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 16.082046508789062,
      "learning_rate": 0.00012568147258031897,
      "loss": 1.6634,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4709333333333333,
      "eval_loss": 1.9394689798355103,
      "eval_runtime": 11.227,
      "eval_samples_per_second": 334.015,
      "eval_steps_per_second": 5.255,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 10.054752349853516,
      "learning_rate": 5.899518490663266e-05,
      "loss": 1.3138,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.49546666666666667,
      "eval_loss": 1.854115605354309,
      "eval_runtime": 11.1661,
      "eval_samples_per_second": 335.838,
      "eval_steps_per_second": 5.284,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 27.30331802368164,
      "learning_rate": 1.534689686405272e-05,
      "loss": 0.9992,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5122666666666666,
      "eval_loss": 1.8023934364318848,
      "eval_runtime": 11.3567,
      "eval_samples_per_second": 330.202,
      "eval_steps_per_second": 5.195,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}