{
  "best_metric": 0.8664,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0822/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": 0.0001,
      "loss": 1.4427,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8192,
      "eval_loss": 0.6601793169975281,
      "eval_runtime": 11.9207,
      "eval_samples_per_second": 314.579,
      "eval_steps_per_second": 4.949,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8046794533729553,
      "learning_rate": 0.0001,
      "loss": 0.4332,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8456,
      "eval_loss": 0.5226349830627441,
      "eval_runtime": 12.0455,
      "eval_samples_per_second": 311.318,
      "eval_steps_per_second": 4.898,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.106738090515137,
      "learning_rate": 0.0001,
      "loss": 0.2495,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8512,
      "eval_loss": 0.5044704675674438,
      "eval_runtime": 12.2247,
      "eval_samples_per_second": 306.755,
      "eval_steps_per_second": 4.826,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 0.1668,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8538666666666667,
      "eval_loss": 0.5418349504470825,
      "eval_runtime": 11.8825,
      "eval_samples_per_second": 315.591,
      "eval_steps_per_second": 4.965,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.722084999084473,
      "learning_rate": 0.0001,
      "loss": 0.1123,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8498666666666667,
      "eval_loss": 0.5668162703514099,
      "eval_runtime": 11.7442,
      "eval_samples_per_second": 319.308,
      "eval_steps_per_second": 5.024,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.18554255366325378,
      "learning_rate": 0.0001,
      "loss": 0.0904,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8586666666666667,
      "eval_loss": 0.552657425403595,
      "eval_runtime": 12.1084,
      "eval_samples_per_second": 309.703,
      "eval_steps_per_second": 4.873,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.041983988136053085,
      "learning_rate": 0.0001,
      "loss": 0.0763,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8648,
      "eval_loss": 0.5328397750854492,
      "eval_runtime": 11.7455,
      "eval_samples_per_second": 319.271,
      "eval_steps_per_second": 5.023,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.021547002717852592,
      "learning_rate": 0.0001,
      "loss": 0.0577,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8664,
      "eval_loss": 0.5486475229263306,
      "eval_runtime": 12.2306,
      "eval_samples_per_second": 306.609,
      "eval_steps_per_second": 4.824,
      "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
}