{
  "best_metric": 0.4736,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0669/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": 3.3187,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.2192,
      "eval_loss": 2.896721839904785,
      "eval_runtime": 6.4199,
      "eval_samples_per_second": 584.117,
      "eval_steps_per_second": 9.19,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 11.223249435424805,
      "learning_rate": 0.0005,
      "loss": 2.7218,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3021333333333333,
      "eval_loss": 2.571103096008301,
      "eval_runtime": 6.1951,
      "eval_samples_per_second": 605.319,
      "eval_steps_per_second": 9.524,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 2.411,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3432,
      "eval_loss": 2.335266351699829,
      "eval_runtime": 6.1449,
      "eval_samples_per_second": 610.265,
      "eval_steps_per_second": 9.602,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.828548431396484,
      "learning_rate": 0.0005,
      "loss": 2.1698,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.3722666666666667,
      "eval_loss": 2.2428016662597656,
      "eval_runtime": 6.2533,
      "eval_samples_per_second": 599.679,
      "eval_steps_per_second": 9.435,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0005,
      "loss": 1.9709,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.4168,
      "eval_loss": 2.1270248889923096,
      "eval_runtime": 6.3956,
      "eval_samples_per_second": 586.342,
      "eval_steps_per_second": 9.225,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 5.488090991973877,
      "learning_rate": 0.0005,
      "loss": 1.7623,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.4285333333333333,
      "eval_loss": 2.0496411323547363,
      "eval_runtime": 6.6426,
      "eval_samples_per_second": 564.541,
      "eval_steps_per_second": 8.882,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 18.48086166381836,
      "learning_rate": 0.0005,
      "loss": 1.6014,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.4570666666666667,
      "eval_loss": 1.9149764776229858,
      "eval_runtime": 6.2276,
      "eval_samples_per_second": 602.162,
      "eval_steps_per_second": 9.474,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 22.986616134643555,
      "learning_rate": 0.0005,
      "loss": 1.4135,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.4736,
      "eval_loss": 1.899843692779541,
      "eval_runtime": 8.773,
      "eval_samples_per_second": 427.449,
      "eval_steps_per_second": 6.725,
      "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
}