{
  "best_metric": 0.5832,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0199/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": 3.0656,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2674666666666667,
      "eval_loss": 2.7078702449798584,
      "eval_runtime": 7.246,
      "eval_samples_per_second": 517.528,
      "eval_steps_per_second": 8.142,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.2848,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.38293333333333335,
      "eval_loss": 2.2318339347839355,
      "eval_runtime": 6.2044,
      "eval_samples_per_second": 604.409,
      "eval_steps_per_second": 9.509,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.975789070129395,
      "learning_rate": 0.0005,
      "loss": 1.8394,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4448,
      "eval_loss": 1.927485704421997,
      "eval_runtime": 6.2014,
      "eval_samples_per_second": 604.705,
      "eval_steps_per_second": 9.514,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 14.762651443481445,
      "learning_rate": 0.0005,
      "loss": 1.4845,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.47413333333333335,
      "eval_loss": 1.8351178169250488,
      "eval_runtime": 6.2065,
      "eval_samples_per_second": 604.203,
      "eval_steps_per_second": 9.506,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 16.59786033630371,
      "learning_rate": 0.0005,
      "loss": 1.1734,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5453333333333333,
      "eval_loss": 1.6193104982376099,
      "eval_runtime": 6.8488,
      "eval_samples_per_second": 547.541,
      "eval_steps_per_second": 8.615,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 5.3426103591918945,
      "learning_rate": 0.0005,
      "loss": 0.9031,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5650666666666667,
      "eval_loss": 1.5782021284103394,
      "eval_runtime": 6.1855,
      "eval_samples_per_second": 606.261,
      "eval_steps_per_second": 9.539,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 5.720869541168213,
      "learning_rate": 0.0005,
      "loss": 0.6624,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5605333333333333,
      "eval_loss": 1.6713838577270508,
      "eval_runtime": 6.2528,
      "eval_samples_per_second": 599.727,
      "eval_steps_per_second": 9.436,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.365656852722168,
      "learning_rate": 0.0005,
      "loss": 0.4863,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5832,
      "eval_loss": 1.6694079637527466,
      "eval_runtime": 6.198,
      "eval_samples_per_second": 605.036,
      "eval_steps_per_second": 9.519,
      "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
}