{
  "best_metric": 0.8704,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0300/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": 0.0002910075938432782,
      "loss": 2.3497,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.676,
      "eval_loss": 1.1186846494674683,
      "eval_runtime": 12.4153,
      "eval_samples_per_second": 302.046,
      "eval_steps_per_second": 4.752,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.686123847961426,
      "learning_rate": 0.0002650076732300463,
      "loss": 0.8042,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7626666666666667,
      "eval_loss": 0.7940862774848938,
      "eval_runtime": 11.6738,
      "eval_samples_per_second": 321.233,
      "eval_steps_per_second": 5.054,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00022527217722455154,
      "loss": 0.3985,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8101333333333334,
      "eval_loss": 0.6308706402778625,
      "eval_runtime": 11.3652,
      "eval_samples_per_second": 329.954,
      "eval_steps_per_second": 5.191,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 17.17072868347168,
      "learning_rate": 0.00017635686535718819,
      "loss": 0.1904,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8154666666666667,
      "eval_loss": 0.6509622931480408,
      "eval_runtime": 12.2533,
      "eval_samples_per_second": 306.041,
      "eval_steps_per_second": 4.815,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.24526135623455048,
      "learning_rate": 0.00012426252654184345,
      "loss": 0.0756,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8290666666666666,
      "eval_loss": 0.6135759949684143,
      "eval_runtime": 11.991,
      "eval_samples_per_second": 312.735,
      "eval_steps_per_second": 4.92,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.033159367740154266,
      "learning_rate": 7.527250687020608e-05,
      "loss": 0.0198,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8562666666666666,
      "eval_loss": 0.5481571555137634,
      "eval_runtime": 12.2705,
      "eval_samples_per_second": 305.61,
      "eval_steps_per_second": 4.808,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.08213350921869278,
      "learning_rate": 3.5295725730362477e-05,
      "loss": 0.0042,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8685333333333334,
      "eval_loss": 0.5243508815765381,
      "eval_runtime": 12.1313,
      "eval_samples_per_second": 309.118,
      "eval_steps_per_second": 4.863,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.008121575228869915,
      "learning_rate": 9.15397292223129e-06,
      "loss": 0.0018,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8704,
      "eval_loss": 0.5199509859085083,
      "eval_runtime": 11.9853,
      "eval_samples_per_second": 312.883,
      "eval_steps_per_second": 4.923,
      "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
}