{
  "best_metric": 0.9605333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0079/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": 4.667026293130983e-05,
      "loss": 0.7839,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9453333333333334,
      "eval_loss": 0.20433251559734344,
      "eval_runtime": 14.0255,
      "eval_samples_per_second": 267.37,
      "eval_steps_per_second": 4.207,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0846765786409378,
      "learning_rate": 3.7534027314690145e-05,
      "loss": 0.0998,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9464,
      "eval_loss": 0.18753352761268616,
      "eval_runtime": 10.9951,
      "eval_samples_per_second": 341.06,
      "eval_steps_per_second": 5.366,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.03593283146619797,
      "learning_rate": 2.5039309201189614e-05,
      "loss": 0.0343,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9517333333333333,
      "eval_loss": 0.16945618391036987,
      "eval_runtime": 11.4017,
      "eval_samples_per_second": 328.898,
      "eval_steps_per_second": 5.175,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.12723416090011597,
      "learning_rate": 1.253405821897521e-05,
      "loss": 0.0099,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9570666666666666,
      "eval_loss": 0.1606759876012802,
      "eval_runtime": 11.2826,
      "eval_samples_per_second": 332.37,
      "eval_steps_per_second": 5.229,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.16092918813228607,
      "learning_rate": 3.3690462698797944e-06,
      "loss": 0.0044,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9584,
      "eval_loss": 0.15118688344955444,
      "eval_runtime": 10.7855,
      "eval_samples_per_second": 347.688,
      "eval_steps_per_second": 5.47,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.04256497696042061,
      "learning_rate": 3.0904285064359275e-11,
      "loss": 0.0035,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9605333333333334,
      "eval_loss": 0.14810509979724884,
      "eval_runtime": 10.8011,
      "eval_samples_per_second": 347.188,
      "eval_steps_per_second": 5.462,
      "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
}