{
  "best_metric": 0.12152263522148132,
  "best_model_checkpoint": "2025-01-21-14-35-49-resnet-50/checkpoint-340",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "train_accuracy": 0.3101851851851852
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.0346343517303467,
      "learning_rate": 0.0002,
      "loss": 1.5858,
      "step": 34
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5417858897169242,
      "eval_error_rate": 0.4582141102830758,
      "eval_f1": 0.5137841954124206,
      "eval_loss": 1.5129398107528687,
      "eval_precision": 0.6582990397805213,
      "eval_recall": 0.5407407407407407,
      "eval_runtime": 2.4161,
      "eval_samples_per_second": 55.876,
      "eval_steps_per_second": 2.069,
      "eval_top1_accuracy": 0.5407407407407407,
      "step": 34
    },
    {
      "epoch": 2.0,
      "train_accuracy": 0.5728395061728395
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.1958796977996826,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.3909,
      "step": 68
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6521766101076446,
      "eval_error_rate": 0.3478233898923554,
      "eval_f1": 0.6536515615585383,
      "eval_loss": 1.1807034015655518,
      "eval_precision": 0.7779355281207133,
      "eval_recall": 0.6518518518518519,
      "eval_runtime": 4.1739,
      "eval_samples_per_second": 32.344,
      "eval_steps_per_second": 1.198,
      "eval_top1_accuracy": 0.6518518518518519,
      "step": 68
    },
    {
      "epoch": 3.0,
      "train_accuracy": 0.7555555555555555
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.4177141189575195,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.059,
      "step": 102
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8900945083014047,
      "eval_error_rate": 0.10990549169859531,
      "eval_f1": 0.8866714143284432,
      "eval_loss": 0.7502983212471008,
      "eval_precision": 0.8897193885365928,
      "eval_recall": 0.8888888888888888,
      "eval_runtime": 2.3088,
      "eval_samples_per_second": 58.472,
      "eval_steps_per_second": 2.166,
      "eval_top1_accuracy": 0.8888888888888888,
      "step": 102
    },
    {
      "epoch": 4.0,
      "train_accuracy": 0.8592592592592593
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.0578341484069824,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.6942,
      "step": 136
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9427024265644957,
      "eval_error_rate": 0.057297573435504345,
      "eval_f1": 0.9402247755309655,
      "eval_loss": 0.4028763771057129,
      "eval_precision": 0.9427357184700735,
      "eval_recall": 0.9407407407407408,
      "eval_runtime": 2.5361,
      "eval_samples_per_second": 53.231,
      "eval_steps_per_second": 1.972,
      "eval_top1_accuracy": 0.9407407407407408,
      "step": 136
    },
    {
      "epoch": 5.0,
      "train_accuracy": 0.9053497942386831
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.6328682899475098,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.4241,
      "step": 170
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9655172413793103,
      "eval_error_rate": 0.034482758620689724,
      "eval_f1": 0.9623783038619923,
      "eval_loss": 0.23254607617855072,
      "eval_precision": 0.9673052362707535,
      "eval_recall": 0.9629629629629629,
      "eval_runtime": 2.324,
      "eval_samples_per_second": 58.089,
      "eval_steps_per_second": 2.151,
      "eval_top1_accuracy": 0.9629629629629629,
      "step": 170
    },
    {
      "epoch": 6.0,
      "train_accuracy": 0.9308641975308642
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.1090431213378906,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.3235,
      "step": 204
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9650063856960408,
      "eval_error_rate": 0.0349936143039592,
      "eval_f1": 0.9629629629629629,
      "eval_loss": 0.17022636532783508,
      "eval_precision": 0.9673241568516152,
      "eval_recall": 0.9629629629629629,
      "eval_runtime": 2.6075,
      "eval_samples_per_second": 51.773,
      "eval_steps_per_second": 1.918,
      "eval_top1_accuracy": 0.9629629629629629,
      "step": 204
    },
    {
      "epoch": 7.0,
      "train_accuracy": 0.9275720164609054
    },
    {
      "epoch": 7.0,
      "grad_norm": 3.2708213329315186,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.259,
      "step": 238
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9719029374201789,
      "eval_error_rate": 0.02809706257982114,
      "eval_f1": 0.9704003194569231,
      "eval_loss": 0.13593700528144836,
      "eval_precision": 0.9722026259063294,
      "eval_recall": 0.9703703703703703,
      "eval_runtime": 2.2366,
      "eval_samples_per_second": 60.359,
      "eval_steps_per_second": 2.236,
      "eval_top1_accuracy": 0.9703703703703703,
      "step": 238
    },
    {
      "epoch": 8.0,
      "train_accuracy": 0.939917695473251
    },
    {
      "epoch": 8.0,
      "grad_norm": 4.090179920196533,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.2231,
      "step": 272
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9719029374201789,
      "eval_error_rate": 0.02809706257982114,
      "eval_f1": 0.9704003194569231,
      "eval_loss": 0.12249229103326797,
      "eval_precision": 0.9722026259063294,
      "eval_recall": 0.9703703703703703,
      "eval_runtime": 2.5602,
      "eval_samples_per_second": 52.73,
      "eval_steps_per_second": 1.953,
      "eval_top1_accuracy": 0.9703703703703703,
      "step": 272
    },
    {
      "epoch": 9.0,
      "train_accuracy": 0.9423868312757202
    },
    {
      "epoch": 9.0,
      "grad_norm": 4.149399280548096,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.2167,
      "step": 306
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9719029374201789,
      "eval_error_rate": 0.02809706257982114,
      "eval_f1": 0.9704003194569231,
      "eval_loss": 0.12528401613235474,
      "eval_precision": 0.9722026259063294,
      "eval_recall": 0.9703703703703703,
      "eval_runtime": 2.3147,
      "eval_samples_per_second": 58.323,
      "eval_steps_per_second": 2.16,
      "eval_top1_accuracy": 0.9703703703703703,
      "step": 306
    },
    {
      "epoch": 10.0,
      "train_accuracy": 0.9481481481481482
    },
    {
      "epoch": 10.0,
      "grad_norm": 5.03872537612915,
      "learning_rate": 0.0,
      "loss": 0.1973,
      "step": 340
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9787994891443168,
      "eval_error_rate": 0.021200510855683197,
      "eval_f1": 0.9777978650868422,
      "eval_loss": 0.12152263522148132,
      "eval_precision": 0.9786106212032138,
      "eval_recall": 0.9777777777777777,
      "eval_runtime": 2.4325,
      "eval_samples_per_second": 55.497,
      "eval_steps_per_second": 2.055,
      "eval_top1_accuracy": 0.9777777777777777,
      "step": 340
    },
    {
      "epoch": 10.0,
      "step": 340,
      "total_flos": 2.294023161765888e+17,
      "train_loss": 0.6373719860525692,
      "train_runtime": 220.4893,
      "train_samples_per_second": 48.982,
      "train_steps_per_second": 1.542
    }
  ],
  "logging_steps": 1,
  "max_steps": 340,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.294023161765888e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}