{
  "best_metric": 0.8784,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0038/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": 6.127627627627627e-05,
      "loss": 1.6541,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7754666666666666,
      "eval_loss": 0.8200030326843262,
      "eval_runtime": 6.2932,
      "eval_samples_per_second": 595.877,
      "eval_steps_per_second": 9.375,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 11.870223999023438,
      "learning_rate": 5.252627627627627e-05,
      "loss": 0.5075,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8328,
      "eval_loss": 0.571956992149353,
      "eval_runtime": 5.8213,
      "eval_samples_per_second": 644.189,
      "eval_steps_per_second": 10.135,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.029247760772705,
      "learning_rate": 4.377627627627627e-05,
      "loss": 0.2697,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8490666666666666,
      "eval_loss": 0.5231208205223083,
      "eval_runtime": 5.7446,
      "eval_samples_per_second": 652.792,
      "eval_steps_per_second": 10.271,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3206851482391357,
      "learning_rate": 3.502627627627627e-05,
      "loss": 0.1358,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8605333333333334,
      "eval_loss": 0.4999929964542389,
      "eval_runtime": 5.69,
      "eval_samples_per_second": 659.052,
      "eval_steps_per_second": 10.369,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 2.630255255255255e-05,
      "loss": 0.0702,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8717333333333334,
      "eval_loss": 0.4781581163406372,
      "eval_runtime": 5.6979,
      "eval_samples_per_second": 658.139,
      "eval_steps_per_second": 10.355,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.3386586904525757,
      "learning_rate": 1.7552552552552552e-05,
      "loss": 0.0291,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8690666666666667,
      "eval_loss": 0.5029466152191162,
      "eval_runtime": 5.7211,
      "eval_samples_per_second": 655.471,
      "eval_steps_per_second": 10.313,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.10238321125507355,
      "learning_rate": 8.802552552552553e-06,
      "loss": 0.012,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8762666666666666,
      "eval_loss": 0.4907965362071991,
      "eval_runtime": 6.2186,
      "eval_samples_per_second": 603.033,
      "eval_steps_per_second": 9.488,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.4889802634716034,
      "learning_rate": 5.255255255255255e-08,
      "loss": 0.0061,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8784,
      "eval_loss": 0.49016568064689636,
      "eval_runtime": 5.8588,
      "eval_samples_per_second": 640.066,
      "eval_steps_per_second": 10.07,
      "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
}