{
  "best_metric": 0.5088,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0153/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": 0.0005,
      "loss": 3.2756,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.22346666666666667,
      "eval_loss": 2.916926622390747,
      "eval_runtime": 12.4057,
      "eval_samples_per_second": 302.28,
      "eval_steps_per_second": 4.756,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.6533,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.312,
      "eval_loss": 2.4877517223358154,
      "eval_runtime": 12.5665,
      "eval_samples_per_second": 298.412,
      "eval_steps_per_second": 4.695,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 13.973004341125488,
      "learning_rate": 0.0005,
      "loss": 2.2627,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3794666666666667,
      "eval_loss": 2.2036070823669434,
      "eval_runtime": 12.3116,
      "eval_samples_per_second": 304.592,
      "eval_steps_per_second": 4.792,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.669824123382568,
      "learning_rate": 0.0005,
      "loss": 1.9763,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.4010666666666667,
      "eval_loss": 2.1753790378570557,
      "eval_runtime": 12.4203,
      "eval_samples_per_second": 301.925,
      "eval_steps_per_second": 4.75,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 15.5807523727417,
      "learning_rate": 0.0005,
      "loss": 1.742,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.444,
      "eval_loss": 1.9781163930892944,
      "eval_runtime": 12.6992,
      "eval_samples_per_second": 295.295,
      "eval_steps_per_second": 4.646,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.3783183097839355,
      "learning_rate": 0.0005,
      "loss": 1.5194,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4752,
      "eval_loss": 1.8767075538635254,
      "eval_runtime": 11.8216,
      "eval_samples_per_second": 317.217,
      "eval_steps_per_second": 4.991,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 13.551149368286133,
      "learning_rate": 0.0005,
      "loss": 1.3008,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.49893333333333334,
      "eval_loss": 1.8106523752212524,
      "eval_runtime": 12.3293,
      "eval_samples_per_second": 304.153,
      "eval_steps_per_second": 4.785,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 6.501110076904297,
      "learning_rate": 0.0005,
      "loss": 1.077,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5088,
      "eval_loss": 1.7812398672103882,
      "eval_runtime": 12.5121,
      "eval_samples_per_second": 299.711,
      "eval_steps_per_second": 4.715,
      "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
}