{
  "best_metric": 0.9530666666666666,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0973/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": 0.3459686040878296,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.8737,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9309333333333333,
      "eval_loss": 0.25418713688850403,
      "eval_runtime": 4.4433,
      "eval_samples_per_second": 843.961,
      "eval_steps_per_second": 13.278,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7998790740966797,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.1233,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9368,
      "eval_loss": 0.22817035019397736,
      "eval_runtime": 4.6398,
      "eval_samples_per_second": 808.226,
      "eval_steps_per_second": 12.716,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.867830753326416,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.0373,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9464,
      "eval_loss": 0.19879227876663208,
      "eval_runtime": 4.1351,
      "eval_samples_per_second": 906.869,
      "eval_steps_per_second": 14.268,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.025567123666405678,
      "learning_rate": 2.5e-05,
      "loss": 0.013,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9474666666666667,
      "eval_loss": 0.1966223567724228,
      "eval_runtime": 4.1043,
      "eval_samples_per_second": 913.668,
      "eval_steps_per_second": 14.375,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.048936352133750916,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.0053,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9509333333333333,
      "eval_loss": 0.1998991072177887,
      "eval_runtime": 4.0718,
      "eval_samples_per_second": 920.978,
      "eval_steps_per_second": 14.49,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.013532386161386967,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.0027,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9528,
      "eval_loss": 0.19130685925483704,
      "eval_runtime": 4.148,
      "eval_samples_per_second": 904.047,
      "eval_steps_per_second": 14.224,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": NaN,
      "learning_rate": 1.91430998468726e-06,
      "loss": 0.0022,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9522666666666667,
      "eval_loss": 0.189799502491951,
      "eval_runtime": 4.1258,
      "eval_samples_per_second": 908.91,
      "eval_steps_per_second": 14.3,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.05273326113820076,
      "learning_rate": 1.7383661915504334e-11,
      "loss": 0.0019,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9530666666666666,
      "eval_loss": 0.1897537112236023,
      "eval_runtime": 4.4277,
      "eval_samples_per_second": 846.939,
      "eval_steps_per_second": 13.325,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}