{
  "best_metric": 0.38,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0418/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": 20.60164451599121,
      "learning_rate": 0.0004670935782735732,
      "loss": 3.4598,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1824,
      "eval_loss": 3.0810768604278564,
      "eval_runtime": 13.5731,
      "eval_samples_per_second": 276.282,
      "eval_steps_per_second": 4.347,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 14.919262886047363,
      "learning_rate": 0.00037601988894783115,
      "loss": 2.9347,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2352,
      "eval_loss": 2.8451859951019287,
      "eval_runtime": 13.7017,
      "eval_samples_per_second": 273.688,
      "eval_steps_per_second": 4.306,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.4514102935791,
      "learning_rate": 0.00025117927214825806,
      "loss": 2.7089,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.28186666666666665,
      "eval_loss": 2.6445655822753906,
      "eval_runtime": 13.5047,
      "eval_samples_per_second": 277.68,
      "eval_steps_per_second": 4.369,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 23.04988670349121,
      "learning_rate": 0.00012602267032890265,
      "loss": 2.4668,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.33493333333333336,
      "eval_loss": 2.4460458755493164,
      "eval_runtime": 13.8061,
      "eval_samples_per_second": 271.619,
      "eval_steps_per_second": 4.273,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 13.138303756713867,
      "learning_rate": 3.408569387468488e-05,
      "loss": 2.2228,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.36666666666666664,
      "eval_loss": 2.28456974029541,
      "eval_runtime": 14.1513,
      "eval_samples_per_second": 264.994,
      "eval_steps_per_second": 4.169,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 13.491533279418945,
      "learning_rate": 2.7813810714871766e-09,
      "loss": 2.0615,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.38,
      "eval_loss": 2.2695415019989014,
      "eval_runtime": 13.5002,
      "eval_samples_per_second": 277.773,
      "eval_steps_per_second": 4.37,
      "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
}