{
  "best_metric": 0.8728,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0097/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": 2.2555,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7546666666666667,
      "eval_loss": 1.1135178804397583,
      "eval_runtime": 6.2657,
      "eval_samples_per_second": 598.501,
      "eval_steps_per_second": 9.416,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.9073864221572876,
      "learning_rate": 3e-05,
      "loss": 0.7244,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8258666666666666,
      "eval_loss": 0.6475999355316162,
      "eval_runtime": 6.5149,
      "eval_samples_per_second": 575.603,
      "eval_steps_per_second": 9.056,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.183158874511719,
      "learning_rate": 3e-05,
      "loss": 0.4005,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.864,
      "eval_loss": 0.4944806694984436,
      "eval_runtime": 7.0258,
      "eval_samples_per_second": 533.747,
      "eval_steps_per_second": 8.398,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.071652889251709,
      "learning_rate": 3e-05,
      "loss": 0.2603,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8610666666666666,
      "eval_loss": 0.4801841378211975,
      "eval_runtime": 6.3401,
      "eval_samples_per_second": 591.472,
      "eval_steps_per_second": 9.306,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3332628607749939,
      "learning_rate": 3e-05,
      "loss": 0.1728,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8584,
      "eval_loss": 0.47034862637519836,
      "eval_runtime": 7.3678,
      "eval_samples_per_second": 508.975,
      "eval_steps_per_second": 8.008,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 51.96931457519531,
      "learning_rate": 3e-05,
      "loss": 0.1218,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8626666666666667,
      "eval_loss": 0.47203582525253296,
      "eval_runtime": 6.3834,
      "eval_samples_per_second": 587.459,
      "eval_steps_per_second": 9.243,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 7.456040859222412,
      "learning_rate": 3e-05,
      "loss": 0.0853,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8688,
      "eval_loss": 0.4941895604133606,
      "eval_runtime": 6.3933,
      "eval_samples_per_second": 586.549,
      "eval_steps_per_second": 9.228,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.0691,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8728,
      "eval_loss": 0.49118688702583313,
      "eval_runtime": 6.4976,
      "eval_samples_per_second": 577.137,
      "eval_steps_per_second": 9.08,
      "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
}