trainer_state.json

{
  "best_metric": 0.6666666666666666,
  "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": 0.3333333333333333,
      "train_auc_class_0": 0.6000000000000001,
      "train_auc_class_1": 0.42,
      "train_auc_class_2": 0.41999999999999993,
      "train_auc_overall": 0.48,
      "train_loss": 1.1545398235321045,
      "train_runtime": 1.8894,
      "train_samples_per_second": 7.939,
      "train_steps_per_second": 0.529
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5,
      "eval_auc_class_0": 0.625,
      "eval_auc_class_1": 0.25,
      "eval_auc_class_2": 0.75,
      "eval_auc_overall": 0.5416666666666666,
      "eval_loss": 1.1536046266555786,
      "eval_runtime": 0.6925,
      "eval_samples_per_second": 8.665,
      "eval_steps_per_second": 1.444,
      "step": 1
    },
    {
      "epoch": 2.0,
      "step": 2,
      "train_accuracy": 0.6,
      "train_auc_class_0": 0.8400000000000001,
      "train_auc_class_1": 0.7200000000000001,
      "train_auc_class_2": 0.8600000000000001,
      "train_auc_overall": 0.8066666666666666,
      "train_loss": 0.87682044506073,
      "train_runtime": 1.6553,
      "train_samples_per_second": 9.062,
      "train_steps_per_second": 0.604
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_auc_class_0": 0.625,
      "eval_auc_class_1": 0.5,
      "eval_auc_class_2": 1.0,
      "eval_auc_overall": 0.7083333333333334,
      "eval_loss": 0.9763297438621521,
      "eval_runtime": 0.6997,
      "eval_samples_per_second": 8.575,
      "eval_steps_per_second": 1.429,
      "step": 2
    },
    {
      "epoch": 3.0,
      "step": 3,
      "train_accuracy": 0.8666666666666667,
      "train_auc_class_0": 0.88,
      "train_auc_class_1": 0.96,
      "train_auc_class_2": 1.0,
      "train_auc_overall": 0.9466666666666667,
      "train_loss": 0.6894626617431641,
      "train_runtime": 1.7265,
      "train_samples_per_second": 8.688,
      "train_steps_per_second": 0.579
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_auc_class_0": 0.75,
      "eval_auc_class_1": 0.625,
      "eval_auc_class_2": 1.0,
      "eval_auc_overall": 0.7916666666666666,
      "eval_loss": 0.9298850893974304,
      "eval_runtime": 0.7147,
      "eval_samples_per_second": 8.395,
      "eval_steps_per_second": 1.399,
      "step": 3
    },
    {
      "epoch": 3.0,
      "step": 3,
      "total_flos": 3525591661885440.0,
      "train_loss": 0.24405852953592935,
      "train_runtime": 72.8636,
      "train_samples_per_second": 0.618,
      "train_steps_per_second": 0.041
    },
    {
      "epoch": 3.0,
      "step": 3,
      "train_accuracy": 0.7333333333333333,
      "train_auc_class_0": 0.8400000000000001,
      "train_auc_class_1": 0.9199999999999999,
      "train_auc_class_2": 1.0,
      "train_auc_overall": 0.9199999999999999,
      "train_loss": 0.7121346592903137,
      "train_runtime": 1.6755,
      "train_samples_per_second": 8.952,
      "train_steps_per_second": 0.597
    }
  ],
  "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
}