trainer_state.json

{
  "best_metric": 0.3333333333333333,
  "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-cons_Classification_base_V10/checkpoint-2",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "step": 1,
      "train_accuracy": 0.2,
      "train_auc_class_0": 0.52,
      "train_auc_class_1": 0.32,
      "train_auc_class_2": 0.44000000000000006,
      "train_auc_overall": 0.42666666666666675,
      "train_loss": 1.2085740566253662,
      "train_runtime": 1.8632,
      "train_samples_per_second": 8.051,
      "train_steps_per_second": 0.537
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.16666666666666666,
      "eval_auc_class_0": 0.375,
      "eval_auc_class_1": 0.25,
      "eval_auc_class_2": 0.625,
      "eval_auc_overall": 0.4166666666666667,
      "eval_loss": 1.1931848526000977,
      "eval_runtime": 0.71,
      "eval_samples_per_second": 8.451,
      "eval_steps_per_second": 1.409,
      "step": 1
    },
    {
      "epoch": 2.0,
      "step": 2,
      "train_accuracy": 0.6,
      "train_auc_class_0": 0.8800000000000001,
      "train_auc_class_1": 0.78,
      "train_auc_class_2": 0.96,
      "train_auc_overall": 0.8733333333333334,
      "train_loss": 0.8179279565811157,
      "train_runtime": 1.6625,
      "train_samples_per_second": 9.022,
      "train_steps_per_second": 0.601
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3333333333333333,
      "eval_auc_class_0": 0.375,
      "eval_auc_class_1": 0.875,
      "eval_auc_class_2": 0.75,
      "eval_auc_overall": 0.6666666666666666,
      "eval_loss": 1.0399374961853027,
      "eval_runtime": 0.7076,
      "eval_samples_per_second": 8.48,
      "eval_steps_per_second": 1.413,
      "step": 2
    },
    {
      "epoch": 3.0,
      "step": 3,
      "train_accuracy": 0.6666666666666666,
      "train_auc_class_0": 0.88,
      "train_auc_class_1": 0.9400000000000001,
      "train_auc_class_2": 0.96,
      "train_auc_overall": 0.9266666666666667,
      "train_loss": 0.7590439319610596,
      "train_runtime": 1.5813,
      "train_samples_per_second": 9.486,
      "train_steps_per_second": 0.632
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3333333333333333,
      "eval_auc_class_0": 0.5,
      "eval_auc_class_1": 1.0,
      "eval_auc_class_2": 0.75,
      "eval_auc_overall": 0.75,
      "eval_loss": 0.9920186996459961,
      "eval_runtime": 0.6966,
      "eval_samples_per_second": 8.613,
      "eval_steps_per_second": 1.435,
      "step": 3
    },
    {
      "epoch": 3.0,
      "step": 3,
      "total_flos": 3525591661885440.0,
      "train_loss": 0.25828051567077637,
      "train_runtime": 73.8621,
      "train_samples_per_second": 0.609,
      "train_steps_per_second": 0.041
    },
    {
      "epoch": 3.0,
      "step": 3,
      "train_accuracy": 0.6666666666666666,
      "train_auc_class_0": 0.8200000000000001,
      "train_auc_class_1": 0.92,
      "train_auc_class_2": 0.7200000000000001,
      "train_auc_overall": 0.8200000000000002,
      "train_loss": 0.9375088214874268,
      "train_runtime": 1.5198,
      "train_samples_per_second": 9.87,
      "train_steps_per_second": 0.658
    }
  ],
  "logging_steps": 10,
  "max_steps": 3,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3525591661885440.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}