trainer_state.json

{
  "best_metric": 0.5,
  "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-cons_Classification_base_V10/checkpoint-1",
  "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": 0.3333333333333333,
      "train_auc_class_0": 0.52,
      "train_auc_class_1": 0.5800000000000001,
      "train_auc_class_2": 0.22,
      "train_auc_overall": 0.44,
      "train_loss": 1.3131554126739502,
      "train_runtime": 1.6412,
      "train_samples_per_second": 9.14,
      "train_steps_per_second": 0.609
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5,
      "eval_auc_class_0": 0.625,
      "eval_auc_class_1": 0.375,
      "eval_auc_class_2": 0.0,
      "eval_auc_overall": 0.3333333333333333,
      "eval_loss": 1.2536860704421997,
      "eval_runtime": 0.6979,
      "eval_samples_per_second": 8.597,
      "eval_steps_per_second": 1.433,
      "step": 1
    },
    {
      "epoch": 2.0,
      "step": 2,
      "train_accuracy": 0.6666666666666666,
      "train_auc_class_0": 0.7799999999999999,
      "train_auc_class_1": 0.8799999999999999,
      "train_auc_class_2": 0.64,
      "train_auc_overall": 0.7666666666666666,
      "train_loss": 0.9476243853569031,
      "train_runtime": 1.6529,
      "train_samples_per_second": 9.075,
      "train_steps_per_second": 0.605
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3333333333333333,
      "eval_auc_class_0": 0.625,
      "eval_auc_class_1": 0.75,
      "eval_auc_class_2": 0.125,
      "eval_auc_overall": 0.5,
      "eval_loss": 1.089605689048767,
      "eval_runtime": 0.7552,
      "eval_samples_per_second": 7.945,
      "eval_steps_per_second": 1.324,
      "step": 2
    },
    {
      "epoch": 3.0,
      "step": 3,
      "train_accuracy": 0.8,
      "train_auc_class_0": 1.0,
      "train_auc_class_1": 0.98,
      "train_auc_class_2": 0.9199999999999999,
      "train_auc_overall": 0.9666666666666667,
      "train_loss": 0.7161972522735596,
      "train_runtime": 1.7658,
      "train_samples_per_second": 8.495,
      "train_steps_per_second": 0.566
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.3333333333333333,
      "eval_auc_class_0": 0.625,
      "eval_auc_class_1": 1.0,
      "eval_auc_class_2": 0.25,
      "eval_auc_overall": 0.625,
      "eval_loss": 1.0246309041976929,
      "eval_runtime": 0.7191,
      "eval_samples_per_second": 8.344,
      "eval_steps_per_second": 1.391,
      "step": 3
    },
    {
      "epoch": 3.0,
      "step": 3,
      "total_flos": 3525591661885440.0,
      "train_loss": 0.2987220684687297,
      "train_runtime": 73.0126,
      "train_samples_per_second": 0.616,
      "train_steps_per_second": 0.041
    },
    {
      "epoch": 3.0,
      "step": 3,
      "train_accuracy": 0.13333333333333333,
      "train_auc_class_0": 0.39999999999999997,
      "train_auc_class_1": 0.6000000000000001,
      "train_auc_class_2": 0.2,
      "train_auc_overall": 0.39999999999999997,
      "train_loss": 1.3039982318878174,
      "train_runtime": 1.7052,
      "train_samples_per_second": 8.797,
      "train_steps_per_second": 0.586
    }
  ],
  "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
}