{
  "best_metric": 0.9514666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0292/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": 1.114,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9416,
      "eval_loss": 0.23551654815673828,
      "eval_runtime": 7.294,
      "eval_samples_per_second": 514.119,
      "eval_steps_per_second": 8.089,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.47849947214126587,
      "learning_rate": 3e-05,
      "loss": 0.1381,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9445333333333333,
      "eval_loss": 0.19588929414749146,
      "eval_runtime": 8.1222,
      "eval_samples_per_second": 461.696,
      "eval_steps_per_second": 7.264,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.07946855574846268,
      "learning_rate": 3e-05,
      "loss": 0.0498,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9469333333333333,
      "eval_loss": 0.1781175434589386,
      "eval_runtime": 6.8396,
      "eval_samples_per_second": 548.279,
      "eval_steps_per_second": 8.626,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5926623940467834,
      "learning_rate": 3e-05,
      "loss": 0.0201,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.936,
      "eval_loss": 0.258029967546463,
      "eval_runtime": 6.9521,
      "eval_samples_per_second": 539.404,
      "eval_steps_per_second": 8.487,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.019278788939118385,
      "learning_rate": 3e-05,
      "loss": 0.0093,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9458666666666666,
      "eval_loss": 0.20840972661972046,
      "eval_runtime": 6.6829,
      "eval_samples_per_second": 561.136,
      "eval_steps_per_second": 8.829,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.0692797526717186,
      "learning_rate": 3e-05,
      "loss": 0.0056,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9469333333333333,
      "eval_loss": 0.2197677195072174,
      "eval_runtime": 7.5959,
      "eval_samples_per_second": 493.687,
      "eval_steps_per_second": 7.767,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.011340804398059845,
      "learning_rate": 3e-05,
      "loss": 0.0027,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9504,
      "eval_loss": 0.22789496183395386,
      "eval_runtime": 6.4455,
      "eval_samples_per_second": 581.8,
      "eval_steps_per_second": 9.154,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.05186964198946953,
      "learning_rate": 3e-05,
      "loss": 0.0023,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9514666666666667,
      "eval_loss": 0.2179582715034485,
      "eval_runtime": 6.3837,
      "eval_samples_per_second": 587.43,
      "eval_steps_per_second": 9.242,
      "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
}