{
  "best_metric": 0.8624,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0961/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 8.672913551330566,
      "learning_rate": 0.0001,
      "loss": 1.8771,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7610666666666667,
      "eval_loss": 0.8393557667732239,
      "eval_runtime": 6.073,
      "eval_samples_per_second": 617.487,
      "eval_steps_per_second": 9.715,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.769819736480713,
      "learning_rate": 0.0001,
      "loss": 0.5522,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8402666666666667,
      "eval_loss": 0.5442855954170227,
      "eval_runtime": 5.6865,
      "eval_samples_per_second": 659.453,
      "eval_steps_per_second": 10.375,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.2276840209960938,
      "learning_rate": 0.0001,
      "loss": 0.3138,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8352,
      "eval_loss": 0.530314028263092,
      "eval_runtime": 5.6391,
      "eval_samples_per_second": 664.995,
      "eval_steps_per_second": 10.463,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.9980385303497314,
      "learning_rate": 0.0001,
      "loss": 0.2043,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8605333333333334,
      "eval_loss": 0.4879186451435089,
      "eval_runtime": 7.0622,
      "eval_samples_per_second": 530.996,
      "eval_steps_per_second": 8.354,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 0.1491,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8528,
      "eval_loss": 0.5509119033813477,
      "eval_runtime": 6.1416,
      "eval_samples_per_second": 610.585,
      "eval_steps_per_second": 9.607,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.0278856754302979,
      "learning_rate": 0.0001,
      "loss": 0.1126,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8624,
      "eval_loss": 0.5060733556747437,
      "eval_runtime": 6.0467,
      "eval_samples_per_second": 620.168,
      "eval_steps_per_second": 9.757,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}