{
  "best_metric": 0.5976,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0213/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": 0.0004850126564054637,
      "loss": 3.0837,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.25733333333333336,
      "eval_loss": 2.7333695888519287,
      "eval_runtime": 6.6236,
      "eval_samples_per_second": 566.158,
      "eval_steps_per_second": 8.908,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00044184758936602033,
      "loss": 2.4015,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3722666666666667,
      "eval_loss": 2.2300477027893066,
      "eval_runtime": 6.9958,
      "eval_samples_per_second": 536.032,
      "eval_steps_per_second": 8.434,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 10.333170890808105,
      "learning_rate": 0.0003754536287075859,
      "loss": 1.9921,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4424,
      "eval_loss": 1.9544504880905151,
      "eval_runtime": 7.382,
      "eval_samples_per_second": 507.993,
      "eval_steps_per_second": 7.992,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.330759286880493,
      "learning_rate": 0.000293928108928647,
      "loss": 1.5985,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5056,
      "eval_loss": 1.7513554096221924,
      "eval_runtime": 6.7158,
      "eval_samples_per_second": 558.387,
      "eval_steps_per_second": 8.785,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.366968631744385,
      "learning_rate": 0.00020710421090307243,
      "loss": 1.1738,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5549333333333333,
      "eval_loss": 1.5676453113555908,
      "eval_runtime": 7.0643,
      "eval_samples_per_second": 530.835,
      "eval_steps_per_second": 8.352,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00012568147258031897,
      "loss": 0.6809,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5794666666666667,
      "eval_loss": 1.5570169687271118,
      "eval_runtime": 6.6588,
      "eval_samples_per_second": 563.162,
      "eval_steps_per_second": 8.86,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.41170546412467957,
      "learning_rate": 5.899518490663266e-05,
      "loss": 0.2354,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.5912,
      "eval_loss": 1.6310312747955322,
      "eval_runtime": 7.7953,
      "eval_samples_per_second": 481.062,
      "eval_steps_per_second": 7.569,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 22.747289657592773,
      "learning_rate": 1.534689686405272e-05,
      "loss": 0.0488,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5976,
      "eval_loss": 1.6788241863250732,
      "eval_runtime": 6.576,
      "eval_samples_per_second": 570.253,
      "eval_steps_per_second": 8.972,
      "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
}