{
  "best_metric": 0.8781333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0383/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "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": 4.7538820348083834e-05,
      "loss": 2.0682,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7605333333333333,
      "eval_loss": 0.8819195032119751,
      "eval_runtime": 5.5508,
      "eval_samples_per_second": 675.581,
      "eval_steps_per_second": 10.629,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6742545962333679,
      "learning_rate": 4.0613573610928476e-05,
      "loss": 0.6092,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8154666666666667,
      "eval_loss": 0.609695315361023,
      "eval_runtime": 5.4998,
      "eval_samples_per_second": 681.839,
      "eval_steps_per_second": 10.728,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 3.0628700751103485e-05,
      "loss": 0.3489,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8474666666666667,
      "eval_loss": 0.5112069845199585,
      "eval_runtime": 7.0931,
      "eval_samples_per_second": 528.679,
      "eval_steps_per_second": 8.318,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 60.20093536376953,
      "learning_rate": 1.950269447231056e-05,
      "loss": 0.2064,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8608,
      "eval_loss": 0.45676177740097046,
      "eval_runtime": 5.4513,
      "eval_samples_per_second": 687.91,
      "eval_steps_per_second": 10.823,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.4885811805725098,
      "learning_rate": 9.465496973304394e-06,
      "loss": 0.1174,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8733333333333333,
      "eval_loss": 0.4384898543357849,
      "eval_runtime": 5.8044,
      "eval_samples_per_second": 646.06,
      "eval_steps_per_second": 10.165,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.25628915429115295,
      "learning_rate": 2.5050983169121382e-06,
      "loss": 0.0693,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8781333333333333,
      "eval_loss": 0.4264586567878723,
      "eval_runtime": 5.7994,
      "eval_samples_per_second": 646.624,
      "eval_steps_per_second": 10.174,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}