{
  "best_metric": 0.8546666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0417/checkpoints/checkpoint-2331",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 2331,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.150488376617432,
      "learning_rate": 9e-05,
      "loss": 1.6985,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7733333333333333,
      "eval_loss": 0.7734269499778748,
      "eval_runtime": 7.1987,
      "eval_samples_per_second": 520.925,
      "eval_steps_per_second": 8.196,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.325972557067871,
      "learning_rate": 9e-05,
      "loss": 0.5551,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.828,
      "eval_loss": 0.5653694868087769,
      "eval_runtime": 7.1062,
      "eval_samples_per_second": 527.712,
      "eval_steps_per_second": 8.303,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.44498303532600403,
      "learning_rate": 9e-05,
      "loss": 0.3363,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8304,
      "eval_loss": 0.5600535273551941,
      "eval_runtime": 7.0503,
      "eval_samples_per_second": 531.889,
      "eval_steps_per_second": 8.368,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.866662323474884,
      "learning_rate": 9e-05,
      "loss": 0.2304,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8304,
      "eval_loss": 0.5546911358833313,
      "eval_runtime": 7.0204,
      "eval_samples_per_second": 534.161,
      "eval_steps_per_second": 8.404,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.751897931098938,
      "learning_rate": 9e-05,
      "loss": 0.1634,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.848,
      "eval_loss": 0.5269986391067505,
      "eval_runtime": 7.3204,
      "eval_samples_per_second": 512.264,
      "eval_steps_per_second": 8.06,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.1735734939575195,
      "learning_rate": 9e-05,
      "loss": 0.118,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8536,
      "eval_loss": 0.5131481885910034,
      "eval_runtime": 7.6874,
      "eval_samples_per_second": 487.811,
      "eval_steps_per_second": 7.675,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.03226286917924881,
      "learning_rate": 9e-05,
      "loss": 0.0962,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8546666666666667,
      "eval_loss": 0.5516376495361328,
      "eval_runtime": 7.0856,
      "eval_samples_per_second": 529.245,
      "eval_steps_per_second": 8.327,
      "step": 2331
    }
  ],
  "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": 1.153189244358144e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}