{
  "best_metric": 0.892,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0949/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": 4.376876876876877e-05,
      "loss": 2.0542,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7592,
      "eval_loss": 0.9384669065475464,
      "eval_runtime": 13.4589,
      "eval_samples_per_second": 278.626,
      "eval_steps_per_second": 4.384,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 12.504182815551758,
      "learning_rate": 3.7518768768768766e-05,
      "loss": 0.6784,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8133333333333334,
      "eval_loss": 0.6294507384300232,
      "eval_runtime": 12.5838,
      "eval_samples_per_second": 298.002,
      "eval_steps_per_second": 4.689,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3746674954891205,
      "learning_rate": 3.126876876876877e-05,
      "loss": 0.3984,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8672,
      "eval_loss": 0.45056748390197754,
      "eval_runtime": 13.4992,
      "eval_samples_per_second": 277.793,
      "eval_steps_per_second": 4.371,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.27439212799072266,
      "learning_rate": 2.5018768768768767e-05,
      "loss": 0.2569,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8741333333333333,
      "eval_loss": 0.4210956394672394,
      "eval_runtime": 13.3382,
      "eval_samples_per_second": 281.147,
      "eval_steps_per_second": 4.423,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.3656371831893921,
      "learning_rate": 1.8768768768768768e-05,
      "loss": 0.1685,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8749333333333333,
      "eval_loss": 0.4119403064250946,
      "eval_runtime": 13.4471,
      "eval_samples_per_second": 278.87,
      "eval_steps_per_second": 4.388,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.1896754801273346,
      "learning_rate": 1.2518768768768768e-05,
      "loss": 0.1098,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8890666666666667,
      "eval_loss": 0.38129326701164246,
      "eval_runtime": 13.3512,
      "eval_samples_per_second": 280.873,
      "eval_steps_per_second": 4.419,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.45523974299430847,
      "learning_rate": 6.268768768768769e-06,
      "loss": 0.0637,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8904,
      "eval_loss": 0.38298794627189636,
      "eval_runtime": 13.3801,
      "eval_samples_per_second": 280.268,
      "eval_steps_per_second": 4.41,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.7979095578193665,
      "learning_rate": 1.876876876876877e-08,
      "loss": 0.0406,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.892,
      "eval_loss": 0.3684084117412567,
      "eval_runtime": 13.4059,
      "eval_samples_per_second": 279.727,
      "eval_steps_per_second": 4.401,
      "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
}