{
  "best_metric": 0.8466666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0254/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": 3.5519936084747314,
      "learning_rate": 0.0001,
      "loss": 0.8306,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8269333333333333,
      "eval_loss": 0.5950049757957458,
      "eval_runtime": 6.4817,
      "eval_samples_per_second": 578.552,
      "eval_steps_per_second": 9.103,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 0.3435,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8224,
      "eval_loss": 0.6018209457397461,
      "eval_runtime": 5.8152,
      "eval_samples_per_second": 644.856,
      "eval_steps_per_second": 10.146,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.3753260374069214,
      "learning_rate": 0.0001,
      "loss": 0.2455,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8453333333333334,
      "eval_loss": 0.5773780345916748,
      "eval_runtime": 6.016,
      "eval_samples_per_second": 623.342,
      "eval_steps_per_second": 9.807,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 6.457356929779053,
      "learning_rate": 0.0001,
      "loss": 0.1947,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8330666666666666,
      "eval_loss": 0.643925130367279,
      "eval_runtime": 6.0904,
      "eval_samples_per_second": 615.718,
      "eval_steps_per_second": 9.687,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 87.86124420166016,
      "learning_rate": 0.0001,
      "loss": 0.1649,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8317333333333333,
      "eval_loss": 0.680334746837616,
      "eval_runtime": 6.2773,
      "eval_samples_per_second": 597.388,
      "eval_steps_per_second": 9.399,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.029719673097133636,
      "learning_rate": 0.0001,
      "loss": 0.1413,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.836,
      "eval_loss": 0.6800534129142761,
      "eval_runtime": 5.8946,
      "eval_samples_per_second": 636.177,
      "eval_steps_per_second": 10.009,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.6886875629425049,
      "learning_rate": 0.0001,
      "loss": 0.121,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.836,
      "eval_loss": 0.6574221253395081,
      "eval_runtime": 5.7954,
      "eval_samples_per_second": 647.066,
      "eval_steps_per_second": 10.181,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.4383029639720917,
      "learning_rate": 0.0001,
      "loss": 0.1202,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8466666666666667,
      "eval_loss": 0.6559292674064636,
      "eval_runtime": 6.1395,
      "eval_samples_per_second": 610.797,
      "eval_steps_per_second": 9.61,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2997,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}