{
  "best_metric": 0.8573333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0435/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": 0.0002910611396268257,
      "loss": 2.5207,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6304,
      "eval_loss": 1.2969609498977661,
      "eval_runtime": 6.4607,
      "eval_samples_per_second": 580.429,
      "eval_steps_per_second": 9.132,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.7569780349731445,
      "learning_rate": 0.0002651085536196122,
      "loss": 0.9454,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7477333333333334,
      "eval_loss": 0.8340619802474976,
      "eval_runtime": 6.5354,
      "eval_samples_per_second": 573.798,
      "eval_steps_per_second": 9.028,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 7.779026985168457,
      "learning_rate": 0.00022527217722455154,
      "loss": 0.4513,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7952,
      "eval_loss": 0.6835575103759766,
      "eval_runtime": 6.5645,
      "eval_samples_per_second": 571.257,
      "eval_steps_per_second": 8.988,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.18780800700187683,
      "learning_rate": 0.00017635686535718819,
      "loss": 0.1971,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8,
      "eval_loss": 0.715947151184082,
      "eval_runtime": 7.4787,
      "eval_samples_per_second": 501.422,
      "eval_steps_per_second": 7.889,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 7.301678657531738,
      "learning_rate": 0.00012426252654184345,
      "loss": 0.082,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8253333333333334,
      "eval_loss": 0.6529683470726013,
      "eval_runtime": 6.5211,
      "eval_samples_per_second": 575.052,
      "eval_steps_per_second": 9.047,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.9322929382324219,
      "learning_rate": 7.527250687020608e-05,
      "loss": 0.024,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.84,
      "eval_loss": 0.6419132351875305,
      "eval_runtime": 6.4473,
      "eval_samples_per_second": 581.641,
      "eval_steps_per_second": 9.151,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.038650039583444595,
      "learning_rate": 3.5295725730362477e-05,
      "loss": 0.005,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8533333333333334,
      "eval_loss": 0.5957598686218262,
      "eval_runtime": 6.498,
      "eval_samples_per_second": 577.097,
      "eval_steps_per_second": 9.08,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.015033550560474396,
      "learning_rate": 9.15397292223129e-06,
      "loss": 0.0016,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8573333333333333,
      "eval_loss": 0.5854998230934143,
      "eval_runtime": 6.4248,
      "eval_samples_per_second": 583.676,
      "eval_steps_per_second": 9.183,
      "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
}