{
  "best_metric": 0.5474666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0357/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "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": 0.0005,
      "loss": 3.0733,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.26106666666666667,
      "eval_loss": 2.761772871017456,
      "eval_runtime": 6.3601,
      "eval_samples_per_second": 589.611,
      "eval_steps_per_second": 9.277,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.3793,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.39973333333333333,
      "eval_loss": 2.218381881713867,
      "eval_runtime": 6.3344,
      "eval_samples_per_second": 592.006,
      "eval_steps_per_second": 9.314,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 16.185653686523438,
      "learning_rate": 0.0005,
      "loss": 1.9441,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4301333333333333,
      "eval_loss": 2.0103261470794678,
      "eval_runtime": 6.5597,
      "eval_samples_per_second": 571.675,
      "eval_steps_per_second": 8.994,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 11.995404243469238,
      "learning_rate": 0.0005,
      "loss": 1.6277,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.49146666666666666,
      "eval_loss": 1.8178558349609375,
      "eval_runtime": 6.772,
      "eval_samples_per_second": 553.754,
      "eval_steps_per_second": 8.712,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 5.072618007659912,
      "learning_rate": 0.0005,
      "loss": 1.3581,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5474666666666667,
      "eval_loss": 1.635169267654419,
      "eval_runtime": 6.2429,
      "eval_samples_per_second": 600.683,
      "eval_steps_per_second": 9.451,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}