{
  "best_metric": 0.9117333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0943/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": 5.974819183349609,
      "learning_rate": 8.728616793536588e-05,
      "loss": 1.3922,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8221333333333334,
      "eval_loss": 0.6248835921287537,
      "eval_runtime": 6.7486,
      "eval_samples_per_second": 555.669,
      "eval_steps_per_second": 8.743,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 7.95023019690139e-05,
      "loss": 0.391,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8501333333333333,
      "eval_loss": 0.4914975166320801,
      "eval_runtime": 6.5941,
      "eval_samples_per_second": 568.69,
      "eval_steps_per_second": 8.947,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 6.758165316736547e-05,
      "loss": 0.2028,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8786666666666667,
      "eval_loss": 0.4189154803752899,
      "eval_runtime": 6.7617,
      "eval_samples_per_second": 554.594,
      "eval_steps_per_second": 8.726,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.19385027885437,
      "learning_rate": 5.2907059607156464e-05,
      "loss": 0.0928,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8744,
      "eval_loss": 0.4788829982280731,
      "eval_runtime": 6.5365,
      "eval_samples_per_second": 573.706,
      "eval_steps_per_second": 9.026,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.17492927610874176,
      "learning_rate": 3.727875796255304e-05,
      "loss": 0.0468,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.888,
      "eval_loss": 0.4344847798347473,
      "eval_runtime": 6.2396,
      "eval_samples_per_second": 600.998,
      "eval_steps_per_second": 9.456,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.1861046552658081,
      "learning_rate": 2.258175206106183e-05,
      "loss": 0.0143,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9032,
      "eval_loss": 0.3811973035335541,
      "eval_runtime": 6.3743,
      "eval_samples_per_second": 588.298,
      "eval_steps_per_second": 9.256,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.2795913517475128,
      "learning_rate": 1.0588717719108745e-05,
      "loss": 0.0043,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9082666666666667,
      "eval_loss": 0.3740313947200775,
      "eval_runtime": 6.6606,
      "eval_samples_per_second": 563.01,
      "eval_steps_per_second": 8.858,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.05293271690607071,
      "learning_rate": 2.7461918766693875e-06,
      "loss": 0.0024,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9117333333333333,
      "eval_loss": 0.3705005943775177,
      "eval_runtime": 6.2306,
      "eval_samples_per_second": 601.864,
      "eval_steps_per_second": 9.469,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}