{
  "best_metric": 0.4776,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0443/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": 3.1196,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2328,
      "eval_loss": 2.804882287979126,
      "eval_runtime": 6.6905,
      "eval_samples_per_second": 560.498,
      "eval_steps_per_second": 8.819,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.6384,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.30106666666666665,
      "eval_loss": 2.5404183864593506,
      "eval_runtime": 7.3221,
      "eval_samples_per_second": 512.15,
      "eval_steps_per_second": 8.058,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.049911499023438,
      "learning_rate": 0.0005,
      "loss": 2.3349,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3626666666666667,
      "eval_loss": 2.3306615352630615,
      "eval_runtime": 6.9012,
      "eval_samples_per_second": 543.384,
      "eval_steps_per_second": 8.549,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 14.815606117248535,
      "learning_rate": 0.0005,
      "loss": 2.0752,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.38053333333333333,
      "eval_loss": 2.207566499710083,
      "eval_runtime": 6.8991,
      "eval_samples_per_second": 543.546,
      "eval_steps_per_second": 8.552,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.494001388549805,
      "learning_rate": 0.0005,
      "loss": 1.9089,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4416,
      "eval_loss": 1.9731159210205078,
      "eval_runtime": 7.5348,
      "eval_samples_per_second": 497.689,
      "eval_steps_per_second": 7.83,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7250051498413086,
      "learning_rate": 0.0005,
      "loss": 1.7262,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4208,
      "eval_loss": 2.0758862495422363,
      "eval_runtime": 6.9242,
      "eval_samples_per_second": 541.581,
      "eval_steps_per_second": 8.521,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 9.960922241210938,
      "learning_rate": 0.0005,
      "loss": 1.5611,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4688,
      "eval_loss": 1.8878626823425293,
      "eval_runtime": 7.7793,
      "eval_samples_per_second": 482.048,
      "eval_steps_per_second": 7.584,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 1.416,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.4776,
      "eval_loss": 1.8454034328460693,
      "eval_runtime": 6.6677,
      "eval_samples_per_second": 562.414,
      "eval_steps_per_second": 8.849,
      "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
}