{
  "best_metric": 0.8245333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0414/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": Infinity,
      "learning_rate": 0.0002800215775878589,
      "loss": 2.9952,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3589333333333333,
      "eval_loss": 2.3108510971069336,
      "eval_runtime": 13.5759,
      "eval_samples_per_second": 276.225,
      "eval_steps_per_second": 4.346,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00022540814184580826,
      "loss": 1.6374,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6485333333333333,
      "eval_loss": 1.1905689239501953,
      "eval_runtime": 13.0654,
      "eval_samples_per_second": 287.017,
      "eval_steps_per_second": 4.516,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.680152177810669,
      "learning_rate": 0.00015047170983116046,
      "loss": 0.7873,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7418666666666667,
      "eval_loss": 0.857521653175354,
      "eval_runtime": 18.817,
      "eval_samples_per_second": 199.288,
      "eval_steps_per_second": 3.135,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.1063189506530762,
      "learning_rate": 7.540888354819138e-05,
      "loss": 0.3618,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8024,
      "eval_loss": 0.6635573506355286,
      "eval_runtime": 13.1076,
      "eval_samples_per_second": 286.093,
      "eval_steps_per_second": 4.501,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.24483124911785126,
      "learning_rate": 2.0332686681020267e-05,
      "loss": 0.1191,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8242666666666667,
      "eval_loss": 0.6010810136795044,
      "eval_runtime": 13.0136,
      "eval_samples_per_second": 288.16,
      "eval_steps_per_second": 4.534,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.16595809161663055,
      "learning_rate": 7.417023831113311e-10,
      "loss": 0.0451,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8245333333333333,
      "eval_loss": 0.5974944829940796,
      "eval_runtime": 13.2657,
      "eval_samples_per_second": 282.684,
      "eval_steps_per_second": 4.448,
      "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
}