{
  "best_metric": 0.7482666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0156/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": 0.00026261261261261256,
      "loss": 3.1489,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2944,
      "eval_loss": 2.646489143371582,
      "eval_runtime": 12.3946,
      "eval_samples_per_second": 302.55,
      "eval_steps_per_second": 4.76,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002252252252252252,
      "loss": 2.2353,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4653333333333333,
      "eval_loss": 1.93426513671875,
      "eval_runtime": 12.3872,
      "eval_samples_per_second": 302.732,
      "eval_steps_per_second": 4.763,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.759803771972656,
      "learning_rate": 0.00018772522522522518,
      "loss": 1.4811,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5794666666666667,
      "eval_loss": 1.4756659269332886,
      "eval_runtime": 12.0183,
      "eval_samples_per_second": 312.023,
      "eval_steps_per_second": 4.909,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.654964447021484,
      "learning_rate": 0.0001502252252252252,
      "loss": 0.8227,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6682666666666667,
      "eval_loss": 1.1480909585952759,
      "eval_runtime": 12.151,
      "eval_samples_per_second": 308.618,
      "eval_steps_per_second": 4.856,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6444074511528015,
      "learning_rate": 0.00011272522522522522,
      "loss": 0.3325,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7005333333333333,
      "eval_loss": 1.068740963935852,
      "eval_runtime": 11.9301,
      "eval_samples_per_second": 314.331,
      "eval_steps_per_second": 4.945,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.9685933589935303,
      "learning_rate": 7.522522522522523e-05,
      "loss": 0.0914,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7290666666666666,
      "eval_loss": 1.0297428369522095,
      "eval_runtime": 12.0405,
      "eval_samples_per_second": 311.448,
      "eval_steps_per_second": 4.9,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.03553956001996994,
      "learning_rate": 3.7725225225225225e-05,
      "loss": 0.0161,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7418666666666667,
      "eval_loss": 1.025788426399231,
      "eval_runtime": 12.5082,
      "eval_samples_per_second": 299.803,
      "eval_steps_per_second": 4.717,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.28356847167015076,
      "learning_rate": 2.2522522522522522e-07,
      "loss": 0.0037,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7482666666666666,
      "eval_loss": 1.0191012620925903,
      "eval_runtime": 12.0683,
      "eval_samples_per_second": 310.732,
      "eval_steps_per_second": 4.889,
      "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
}