{
  "best_metric": 0.8704,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0082/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": 2.2984,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7296,
      "eval_loss": 1.1646567583084106,
      "eval_runtime": 7.8963,
      "eval_samples_per_second": 474.909,
      "eval_steps_per_second": 7.472,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 0.8122,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8093333333333333,
      "eval_loss": 0.6829714775085449,
      "eval_runtime": 4.415,
      "eval_samples_per_second": 849.372,
      "eval_steps_per_second": 13.363,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.863327026367188,
      "learning_rate": 3e-05,
      "loss": 0.4858,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8437333333333333,
      "eval_loss": 0.5521318912506104,
      "eval_runtime": 4.306,
      "eval_samples_per_second": 870.874,
      "eval_steps_per_second": 13.702,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.1931025981903076,
      "learning_rate": 3e-05,
      "loss": 0.3273,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8493333333333334,
      "eval_loss": 0.48853713274002075,
      "eval_runtime": 4.299,
      "eval_samples_per_second": 872.292,
      "eval_steps_per_second": 13.724,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.796433448791504,
      "learning_rate": 3e-05,
      "loss": 0.235,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8573333333333333,
      "eval_loss": 0.47781363129615784,
      "eval_runtime": 4.2768,
      "eval_samples_per_second": 876.819,
      "eval_steps_per_second": 13.795,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7459361553192139,
      "learning_rate": 3e-05,
      "loss": 0.1699,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8624,
      "eval_loss": 0.4613572359085083,
      "eval_runtime": 4.9198,
      "eval_samples_per_second": 762.227,
      "eval_steps_per_second": 11.992,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 24.143098831176758,
      "learning_rate": 3e-05,
      "loss": 0.1322,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.86,
      "eval_loss": 0.4860924482345581,
      "eval_runtime": 4.3555,
      "eval_samples_per_second": 860.983,
      "eval_steps_per_second": 13.546,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.591985821723938,
      "learning_rate": 3e-05,
      "loss": 0.0993,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8704,
      "eval_loss": 0.485331654548645,
      "eval_runtime": 4.356,
      "eval_samples_per_second": 860.875,
      "eval_steps_per_second": 13.544,
      "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
}