{
  "best_metric": 0.8557333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0068/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": 2.8002157758785897e-05,
      "loss": 2.5265,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6885333333333333,
      "eval_loss": 1.3492546081542969,
      "eval_runtime": 6.2149,
      "eval_samples_per_second": 603.389,
      "eval_steps_per_second": 9.493,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 2.2540814184580827e-05,
      "loss": 0.9323,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8066666666666666,
      "eval_loss": 0.7344489097595215,
      "eval_runtime": 6.2273,
      "eval_samples_per_second": 602.185,
      "eval_steps_per_second": 9.474,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 32.61945724487305,
      "learning_rate": 1.5047170983116048e-05,
      "loss": 0.4688,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8392,
      "eval_loss": 0.5836265683174133,
      "eval_runtime": 6.1594,
      "eval_samples_per_second": 608.824,
      "eval_steps_per_second": 9.579,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 11.313520431518555,
      "learning_rate": 7.5408883548191384e-06,
      "loss": 0.2576,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8506666666666667,
      "eval_loss": 0.5093241333961487,
      "eval_runtime": 6.2429,
      "eval_samples_per_second": 600.678,
      "eval_steps_per_second": 9.451,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": Infinity,
      "learning_rate": 2.045141632481093e-06,
      "loss": 0.1521,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8538666666666667,
      "eval_loss": 0.4911125600337982,
      "eval_runtime": 6.6171,
      "eval_samples_per_second": 566.709,
      "eval_steps_per_second": 8.916,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.0765938758850098,
      "learning_rate": 1.668828642892306e-10,
      "loss": 0.1092,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8557333333333333,
      "eval_loss": 0.49092501401901245,
      "eval_runtime": 6.2335,
      "eval_samples_per_second": 601.585,
      "eval_steps_per_second": 9.465,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}