{
  "best_metric": 0.9232,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0352/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": 2.8559865951538086,
      "learning_rate": 0.0002799038105676658,
      "loss": 0.6926,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.51173335313797,
      "eval_runtime": 12.9493,
      "eval_samples_per_second": 289.591,
      "eval_steps_per_second": 4.556,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.7715314626693726,
      "learning_rate": 0.000225,
      "loss": 0.3156,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8690666666666667,
      "eval_loss": 0.4507071077823639,
      "eval_runtime": 13.212,
      "eval_samples_per_second": 283.833,
      "eval_steps_per_second": 4.466,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.023624541237950325,
      "learning_rate": 0.00015,
      "loss": 0.1732,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8978666666666667,
      "eval_loss": 0.3682684302330017,
      "eval_runtime": 13.0745,
      "eval_samples_per_second": 286.817,
      "eval_steps_per_second": 4.513,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.23884674906730652,
      "learning_rate": 7.500000000000002e-05,
      "loss": 0.0779,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9133333333333333,
      "eval_loss": 0.3263794183731079,
      "eval_runtime": 13.1528,
      "eval_samples_per_second": 285.11,
      "eval_steps_per_second": 4.486,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.11262141168117523,
      "learning_rate": 2.009618943233419e-05,
      "loss": 0.0255,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9216,
      "eval_loss": 0.30674588680267334,
      "eval_runtime": 13.0534,
      "eval_samples_per_second": 287.281,
      "eval_steps_per_second": 4.52,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.004370323847979307,
      "learning_rate": 0.0,
      "loss": 0.0101,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9232,
      "eval_loss": 0.3007335364818573,
      "eval_runtime": 13.0822,
      "eval_samples_per_second": 286.65,
      "eval_steps_per_second": 4.51,
      "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
}