{
  "best_metric": 0.07615971565246582,
  "best_model_checkpoint": "2025-02-05-21-58-41-resnet-50/checkpoint-721",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 927,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "train_accuracy": 0.28471162648764115
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.584263563156128,
      "learning_rate": 0.0002,
      "loss": 2.4636,
      "step": 103
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5823726629787873,
      "eval_error_rate": 0.4176273370212127,
      "eval_f1": 0.5929270791957494,
      "eval_loss": 2.154754877090454,
      "eval_precision": 0.6866708444643892,
      "eval_recall": 0.6292682926829268,
      "eval_runtime": 10.0935,
      "eval_samples_per_second": 40.62,
      "eval_steps_per_second": 1.288,
      "eval_top1_accuracy": 0.6292682926829268,
      "step": 103
    },
    {
      "epoch": 2.0,
      "train_accuracy": 0.720368863574722
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.2492337226867676,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.3967,
      "step": 206
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8743437160779054,
      "eval_error_rate": 0.1256562839220946,
      "eval_f1": 0.8769823548484003,
      "eval_loss": 0.5585801601409912,
      "eval_precision": 0.8893317170713972,
      "eval_recall": 0.8780487804878049,
      "eval_runtime": 8.1523,
      "eval_samples_per_second": 50.292,
      "eval_steps_per_second": 1.595,
      "eval_top1_accuracy": 0.8780487804878049,
      "step": 206
    },
    {
      "epoch": 3.0,
      "train_accuracy": 0.8866286954163276
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.393784761428833,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.4328,
      "step": 309
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9524324562338874,
      "eval_error_rate": 0.04756754376611261,
      "eval_f1": 0.9518375743563098,
      "eval_loss": 0.20998375117778778,
      "eval_precision": 0.9565172518406057,
      "eval_recall": 0.9512195121951219,
      "eval_runtime": 8.4452,
      "eval_samples_per_second": 48.548,
      "eval_steps_per_second": 1.539,
      "eval_top1_accuracy": 0.9512195121951219,
      "step": 309
    },
    {
      "epoch": 4.0,
      "train_accuracy": 0.92324382967182
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.674211502075195,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.2544,
      "step": 412
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.958823798940078,
      "eval_error_rate": 0.041176201059922035,
      "eval_f1": 0.9612761071488952,
      "eval_loss": 0.1413789838552475,
      "eval_precision": 0.9627985812350435,
      "eval_recall": 0.9609756097560975,
      "eval_runtime": 9.5611,
      "eval_samples_per_second": 42.882,
      "eval_steps_per_second": 1.36,
      "eval_top1_accuracy": 0.9609756097560975,
      "step": 412
    },
    {
      "epoch": 5.0,
      "train_accuracy": 0.9541632763764578
    },
    {
      "epoch": 5.0,
      "grad_norm": 5.053682804107666,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.171,
      "step": 515
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9638319094938057,
      "eval_error_rate": 0.036168090506194295,
      "eval_f1": 0.9682546818665395,
      "eval_loss": 0.11268524825572968,
      "eval_precision": 0.9690166293737246,
      "eval_recall": 0.9682926829268292,
      "eval_runtime": 9.0863,
      "eval_samples_per_second": 45.123,
      "eval_steps_per_second": 1.431,
      "eval_top1_accuracy": 0.9682926829268292,
      "step": 515
    },
    {
      "epoch": 6.0,
      "train_accuracy": 0.9582316246270681
    },
    {
      "epoch": 6.0,
      "grad_norm": 5.191859245300293,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.1556,
      "step": 618
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9680975082361487,
      "eval_error_rate": 0.03190249176385129,
      "eval_f1": 0.9706467840988272,
      "eval_loss": 0.09764808416366577,
      "eval_precision": 0.9715023474110591,
      "eval_recall": 0.9707317073170731,
      "eval_runtime": 7.867,
      "eval_samples_per_second": 52.116,
      "eval_steps_per_second": 1.652,
      "eval_top1_accuracy": 0.9707317073170731,
      "step": 618
    },
    {
      "epoch": 7.0,
      "train_accuracy": 0.9693517765120694
    },
    {
      "epoch": 7.0,
      "grad_norm": 13.192668914794922,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.118,
      "step": 721
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9765634013174265,
      "eval_error_rate": 0.02343659868257353,
      "eval_f1": 0.9804014205399844,
      "eval_loss": 0.07615971565246582,
      "eval_precision": 0.9810152386446259,
      "eval_recall": 0.9804878048780488,
      "eval_runtime": 10.4663,
      "eval_samples_per_second": 39.173,
      "eval_steps_per_second": 1.242,
      "eval_top1_accuracy": 0.9804878048780488,
      "step": 721
    },
    {
      "epoch": 8.0,
      "train_accuracy": 0.9712503390290209
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.4042465686798096,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.1142,
      "step": 824
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9812897795903163,
      "eval_error_rate": 0.01871022040968373,
      "eval_f1": 0.9803571227304607,
      "eval_loss": 0.08533048629760742,
      "eval_precision": 0.9809065609961366,
      "eval_recall": 0.9804878048780488,
      "eval_runtime": 9.5505,
      "eval_samples_per_second": 42.93,
      "eval_steps_per_second": 1.361,
      "eval_top1_accuracy": 0.9804878048780488,
      "step": 824
    },
    {
      "epoch": 9.0,
      "train_accuracy": 0.9717927854624356
    },
    {
      "epoch": 9.0,
      "grad_norm": 8.842650413513184,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0978,
      "step": 927
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9788130896136262,
      "eval_error_rate": 0.02118691038637377,
      "eval_f1": 0.9803389295415358,
      "eval_loss": 0.07979268580675125,
      "eval_precision": 0.980763088973181,
      "eval_recall": 0.9804878048780488,
      "eval_runtime": 8.3701,
      "eval_samples_per_second": 48.984,
      "eval_steps_per_second": 1.553,
      "eval_top1_accuracy": 0.9804878048780488,
      "step": 927
    },
    {
      "epoch": 9.0,
      "step": 927,
      "total_flos": 6.268961276565443e+17,
      "train_loss": 0.578233896850125,
      "train_runtime": 713.8479,
      "train_samples_per_second": 45.906,
      "train_steps_per_second": 1.443
    }
  ],
  "logging_steps": 500,
  "max_steps": 1030,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.268961276565443e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}