{
  "best_metric": 0.8704,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0894/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": 9e-05,
      "loss": 1.7733,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7882666666666667,
      "eval_loss": 0.7712703347206116,
      "eval_runtime": 7.6908,
      "eval_samples_per_second": 487.593,
      "eval_steps_per_second": 7.671,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.2784554958343506,
      "learning_rate": 9e-05,
      "loss": 0.5537,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8186666666666667,
      "eval_loss": 0.6216397881507874,
      "eval_runtime": 6.7641,
      "eval_samples_per_second": 554.401,
      "eval_steps_per_second": 8.723,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.01747465133667,
      "learning_rate": 9e-05,
      "loss": 0.3568,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8554666666666667,
      "eval_loss": 0.4959922730922699,
      "eval_runtime": 6.8047,
      "eval_samples_per_second": 551.092,
      "eval_steps_per_second": 8.671,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3301798701286316,
      "learning_rate": 9e-05,
      "loss": 0.2471,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8541333333333333,
      "eval_loss": 0.542737603187561,
      "eval_runtime": 6.7486,
      "eval_samples_per_second": 555.67,
      "eval_steps_per_second": 8.743,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.1985,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8685333333333334,
      "eval_loss": 0.46351686120033264,
      "eval_runtime": 7.3214,
      "eval_samples_per_second": 512.195,
      "eval_steps_per_second": 8.059,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 10.912606239318848,
      "learning_rate": 9e-05,
      "loss": 0.1465,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8592,
      "eval_loss": 0.5249958038330078,
      "eval_runtime": 6.8148,
      "eval_samples_per_second": 550.272,
      "eval_steps_per_second": 8.658,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.023610839620232582,
      "learning_rate": 9e-05,
      "loss": 0.1201,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8522666666666666,
      "eval_loss": 0.5607836842536926,
      "eval_runtime": 6.8786,
      "eval_samples_per_second": 545.166,
      "eval_steps_per_second": 8.577,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 15.527252197265625,
      "learning_rate": 9e-05,
      "loss": 0.1016,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8704,
      "eval_loss": 0.5240203738212585,
      "eval_runtime": 6.7409,
      "eval_samples_per_second": 556.301,
      "eval_steps_per_second": 8.752,
      "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
}