{
  "best_metric": 0.8608,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0345/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": 3e-05,
      "loss": 2.207,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7456,
      "eval_loss": 1.0987306833267212,
      "eval_runtime": 7.8466,
      "eval_samples_per_second": 477.914,
      "eval_steps_per_second": 7.519,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 20.083654403686523,
      "learning_rate": 3e-05,
      "loss": 0.7946,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8050666666666667,
      "eval_loss": 0.6904937028884888,
      "eval_runtime": 6.2019,
      "eval_samples_per_second": 604.653,
      "eval_steps_per_second": 9.513,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 25.697050094604492,
      "learning_rate": 3e-05,
      "loss": 0.4997,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8381333333333333,
      "eval_loss": 0.5394123792648315,
      "eval_runtime": 6.2145,
      "eval_samples_per_second": 603.431,
      "eval_steps_per_second": 9.494,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.353,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8485333333333334,
      "eval_loss": 0.5046327710151672,
      "eval_runtime": 6.2917,
      "eval_samples_per_second": 596.02,
      "eval_steps_per_second": 9.377,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.7914252281188965,
      "learning_rate": 3e-05,
      "loss": 0.261,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8461333333333333,
      "eval_loss": 0.49698132276535034,
      "eval_runtime": 6.226,
      "eval_samples_per_second": 602.312,
      "eval_steps_per_second": 9.476,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.4910885095596313,
      "learning_rate": 3e-05,
      "loss": 0.2065,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8578666666666667,
      "eval_loss": 0.47339537739753723,
      "eval_runtime": 6.7426,
      "eval_samples_per_second": 556.164,
      "eval_steps_per_second": 8.75,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.1567,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8581333333333333,
      "eval_loss": 0.4698493480682373,
      "eval_runtime": 6.2743,
      "eval_samples_per_second": 597.677,
      "eval_steps_per_second": 9.403,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 22.245328903198242,
      "learning_rate": 3e-05,
      "loss": 0.1288,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8608,
      "eval_loss": 0.4530332088470459,
      "eval_runtime": 7.3559,
      "eval_samples_per_second": 509.794,
      "eval_steps_per_second": 8.021,
      "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
}