{
  "best_metric": 0.8605333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0611/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": 2.198,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7757333333333334,
      "eval_loss": 1.0108927488327026,
      "eval_runtime": 10.7844,
      "eval_samples_per_second": 347.725,
      "eval_steps_per_second": 5.471,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.973518371582031,
      "learning_rate": 3e-05,
      "loss": 0.7115,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.836,
      "eval_loss": 0.6269419193267822,
      "eval_runtime": 10.858,
      "eval_samples_per_second": 345.369,
      "eval_steps_per_second": 5.434,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 10.90868091583252,
      "learning_rate": 3e-05,
      "loss": 0.3764,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8517333333333333,
      "eval_loss": 0.5119034647941589,
      "eval_runtime": 10.9953,
      "eval_samples_per_second": 341.055,
      "eval_steps_per_second": 5.366,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.2149,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.4991864562034607,
      "eval_runtime": 11.2751,
      "eval_samples_per_second": 332.592,
      "eval_steps_per_second": 5.233,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.9563746452331543,
      "learning_rate": 3e-05,
      "loss": 0.1224,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8573333333333333,
      "eval_loss": 0.5059030055999756,
      "eval_runtime": 11.3627,
      "eval_samples_per_second": 330.027,
      "eval_steps_per_second": 5.192,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.3435429334640503,
      "learning_rate": 3e-05,
      "loss": 0.0764,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8576,
      "eval_loss": 0.5256074070930481,
      "eval_runtime": 11.4152,
      "eval_samples_per_second": 328.509,
      "eval_steps_per_second": 5.169,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.11292505264282227,
      "learning_rate": 3e-05,
      "loss": 0.0505,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8576,
      "eval_loss": 0.5633859634399414,
      "eval_runtime": 11.1055,
      "eval_samples_per_second": 337.672,
      "eval_steps_per_second": 5.313,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.04606528580188751,
      "learning_rate": 3e-05,
      "loss": 0.0387,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8605333333333334,
      "eval_loss": 0.5683803558349609,
      "eval_runtime": 10.981,
      "eval_samples_per_second": 341.499,
      "eval_steps_per_second": 5.373,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}