{
  "best_metric": 0.9528,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0674/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": 2.7689425945281982,
      "learning_rate": 6.531088913245535e-05,
      "loss": 0.6587,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.24399858713150024,
      "eval_runtime": 10.612,
      "eval_samples_per_second": 353.374,
      "eval_steps_per_second": 5.56,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7505073547363281,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.099,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9416,
      "eval_loss": 0.20100274682044983,
      "eval_runtime": 10.4498,
      "eval_samples_per_second": 358.857,
      "eval_steps_per_second": 5.646,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.04266111180186272,
      "learning_rate": 3.5e-05,
      "loss": 0.0356,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9434666666666667,
      "eval_loss": 0.2142389863729477,
      "eval_runtime": 10.2911,
      "eval_samples_per_second": 364.394,
      "eval_steps_per_second": 5.733,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.03599129989743233,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.0093,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9506666666666667,
      "eval_loss": 0.19323763251304626,
      "eval_runtime": 10.9568,
      "eval_samples_per_second": 342.252,
      "eval_steps_per_second": 5.385,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.16526490449905396,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.0037,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9506666666666667,
      "eval_loss": 0.1856539398431778,
      "eval_runtime": 10.2781,
      "eval_samples_per_second": 364.853,
      "eval_steps_per_second": 5.74,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.012535053305327892,
      "learning_rate": 0.0,
      "loss": 0.0027,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9528,
      "eval_loss": 0.18612277507781982,
      "eval_runtime": 10.6483,
      "eval_samples_per_second": 352.168,
      "eval_steps_per_second": 5.541,
      "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
}