{
  "best_metric": 0.9552,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0913/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": 0.21267104148864746,
      "learning_rate": 4.665063509461097e-05,
      "loss": 0.8331,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.932,
      "eval_loss": 0.2471098005771637,
      "eval_runtime": 12.3715,
      "eval_samples_per_second": 303.115,
      "eval_steps_per_second": 4.769,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.44265016913414,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.1286,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.948,
      "eval_loss": 0.18227915465831757,
      "eval_runtime": 12.5018,
      "eval_samples_per_second": 299.958,
      "eval_steps_per_second": 4.719,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.2917915880680084,
      "learning_rate": 2.5e-05,
      "loss": 0.0525,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9472,
      "eval_loss": 0.18184225261211395,
      "eval_runtime": 13.0294,
      "eval_samples_per_second": 287.811,
      "eval_steps_per_second": 4.528,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.08229196071624756,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.0201,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9506666666666667,
      "eval_loss": 0.18488788604736328,
      "eval_runtime": 12.2706,
      "eval_samples_per_second": 305.608,
      "eval_steps_per_second": 4.808,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.026165321469306946,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.0091,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9509333333333333,
      "eval_loss": 0.1828685849905014,
      "eval_runtime": 12.2992,
      "eval_samples_per_second": 304.899,
      "eval_steps_per_second": 4.797,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.13653616607189178,
      "learning_rate": 0.0,
      "loss": 0.0067,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9552,
      "eval_loss": 0.1717325747013092,
      "eval_runtime": 12.5523,
      "eval_samples_per_second": 298.749,
      "eval_steps_per_second": 4.7,
      "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
}