{
  "best_metric": 0.6197333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0058/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": Infinity,
      "learning_rate": 0.0005,
      "loss": 3.0917,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3005333333333333,
      "eval_loss": 2.589362382888794,
      "eval_runtime": 7.4652,
      "eval_samples_per_second": 502.331,
      "eval_steps_per_second": 7.903,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.3102,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.42346666666666666,
      "eval_loss": 2.076401472091675,
      "eval_runtime": 8.2966,
      "eval_samples_per_second": 451.99,
      "eval_steps_per_second": 7.111,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 17.626646041870117,
      "learning_rate": 0.0005,
      "loss": 1.8737,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4744,
      "eval_loss": 1.8333704471588135,
      "eval_runtime": 6.9074,
      "eval_samples_per_second": 542.898,
      "eval_steps_per_second": 8.542,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.9301629066467285,
      "learning_rate": 0.0005,
      "loss": 1.5676,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5216,
      "eval_loss": 1.678067922592163,
      "eval_runtime": 6.5976,
      "eval_samples_per_second": 568.388,
      "eval_steps_per_second": 8.943,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.2746583223342896,
      "learning_rate": 0.0005,
      "loss": 1.3045,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5610666666666667,
      "eval_loss": 1.5458699464797974,
      "eval_runtime": 6.2295,
      "eval_samples_per_second": 601.975,
      "eval_steps_per_second": 9.471,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 1.1006,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5893333333333334,
      "eval_loss": 1.4474889039993286,
      "eval_runtime": 6.1492,
      "eval_samples_per_second": 609.835,
      "eval_steps_per_second": 9.595,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 13.017149925231934,
      "learning_rate": 0.0005,
      "loss": 0.8991,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.608,
      "eval_loss": 1.4129775762557983,
      "eval_runtime": 6.3031,
      "eval_samples_per_second": 594.949,
      "eval_steps_per_second": 9.361,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 15.217955589294434,
      "learning_rate": 0.0005,
      "loss": 0.7326,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6197333333333334,
      "eval_loss": 1.4237439632415771,
      "eval_runtime": 6.2458,
      "eval_samples_per_second": 600.404,
      "eval_steps_per_second": 9.446,
      "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
}