{
  "best_metric": 0.416,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0810/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": 24.244688034057617,
      "learning_rate": 0.0003,
      "loss": 3.3809,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19866666666666666,
      "eval_loss": 3.031003713607788,
      "eval_runtime": 12.0397,
      "eval_samples_per_second": 311.471,
      "eval_steps_per_second": 4.9,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 20.46824836730957,
      "learning_rate": 0.0003,
      "loss": 2.8508,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.24693333333333334,
      "eval_loss": 2.8405370712280273,
      "eval_runtime": 13.3182,
      "eval_samples_per_second": 281.569,
      "eval_steps_per_second": 4.43,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 25.036766052246094,
      "learning_rate": 0.0003,
      "loss": 2.619,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.30533333333333335,
      "eval_loss": 2.5848236083984375,
      "eval_runtime": 11.6639,
      "eval_samples_per_second": 321.504,
      "eval_steps_per_second": 5.058,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 22.232023239135742,
      "learning_rate": 0.0003,
      "loss": 2.449,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.32293333333333335,
      "eval_loss": 2.450284719467163,
      "eval_runtime": 11.4878,
      "eval_samples_per_second": 326.433,
      "eval_steps_per_second": 5.136,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 16.754337310791016,
      "learning_rate": 0.0003,
      "loss": 2.2944,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3453333333333333,
      "eval_loss": 2.3887264728546143,
      "eval_runtime": 11.7743,
      "eval_samples_per_second": 318.491,
      "eval_steps_per_second": 5.011,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 24.21211051940918,
      "learning_rate": 0.0003,
      "loss": 2.174,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.36693333333333333,
      "eval_loss": 2.3234567642211914,
      "eval_runtime": 11.6233,
      "eval_samples_per_second": 322.627,
      "eval_steps_per_second": 5.076,
      "step": 1998
    },
    {
      "epoch": 7.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0003,
      "loss": 2.0598,
      "step": 2331
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.3970666666666667,
      "eval_loss": 2.204505443572998,
      "eval_runtime": 13.1721,
      "eval_samples_per_second": 284.692,
      "eval_steps_per_second": 4.479,
      "step": 2331
    },
    {
      "epoch": 8.0,
      "grad_norm": 34.00665283203125,
      "learning_rate": 0.0003,
      "loss": 1.9575,
      "step": 2664
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.416,
      "eval_loss": 2.145223617553711,
      "eval_runtime": 11.1415,
      "eval_samples_per_second": 336.58,
      "eval_steps_per_second": 5.296,
      "step": 2664
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 1.317930564980736e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}