{
  "best_metric": 0.36373333333333335,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0255/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": 21.684255599975586,
      "learning_rate": 0.0004174174174174174,
      "loss": 3.5186,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.1776,
      "eval_loss": 3.0852718353271484,
      "eval_runtime": 5.5497,
      "eval_samples_per_second": 675.714,
      "eval_steps_per_second": 10.631,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 15.43441104888916,
      "learning_rate": 0.0003340840840840841,
      "loss": 2.9859,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.2368,
      "eval_loss": 2.900172472000122,
      "eval_runtime": 5.7453,
      "eval_samples_per_second": 652.702,
      "eval_steps_per_second": 10.269,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 18.122608184814453,
      "learning_rate": 0.0002507507507507508,
      "loss": 2.77,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.27466666666666667,
      "eval_loss": 2.697514295578003,
      "eval_runtime": 5.8393,
      "eval_samples_per_second": 642.199,
      "eval_steps_per_second": 10.104,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 25.283424377441406,
      "learning_rate": 0.00016741741741741742,
      "loss": 2.5703,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.30906666666666666,
      "eval_loss": 2.563333749771118,
      "eval_runtime": 5.443,
      "eval_samples_per_second": 688.963,
      "eval_steps_per_second": 10.84,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 28.133739471435547,
      "learning_rate": 8.408408408408409e-05,
      "loss": 2.3474,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.33653333333333335,
      "eval_loss": 2.435533285140991,
      "eval_runtime": 5.5203,
      "eval_samples_per_second": 679.311,
      "eval_steps_per_second": 10.688,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 27.62257194519043,
      "learning_rate": 7.507507507507508e-07,
      "loss": 2.075,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.36373333333333335,
      "eval_loss": 2.3683087825775146,
      "eval_runtime": 6.0952,
      "eval_samples_per_second": 615.243,
      "eval_steps_per_second": 9.68,
      "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
}