trainer_state.json

{
  "best_metric": 0.9032258064516129,
  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-RCC/checkpoint-7",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9032258064516129,
      "eval_auc": 0.5,
      "eval_f1": 0.4745762711864407,
      "eval_loss": 0.3295924961566925,
      "eval_precision": 0.9032258064516129,
      "eval_recall": 1.0,
      "eval_runtime": 1.1464,
      "eval_samples_per_second": 162.249,
      "eval_steps_per_second": 5.234,
      "step": 7
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.9726035594940186,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.4795,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9032258064516129,
      "eval_auc": 0.5,
      "eval_f1": 0.4745762711864407,
      "eval_loss": 0.31294792890548706,
      "eval_precision": 0.9032258064516129,
      "eval_recall": 1.0,
      "eval_runtime": 1.0901,
      "eval_samples_per_second": 170.621,
      "eval_steps_per_second": 5.504,
      "step": 14
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.6543672680854797,
      "learning_rate": 3.968253968253968e-05,
      "loss": 0.2503,
      "step": 20
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9032258064516129,
      "eval_auc": 0.5,
      "eval_f1": 0.4745762711864407,
      "eval_loss": 0.31820589303970337,
      "eval_precision": 0.9032258064516129,
      "eval_recall": 1.0,
      "eval_runtime": 1.1148,
      "eval_samples_per_second": 166.845,
      "eval_steps_per_second": 5.382,
      "step": 21
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9032258064516129,
      "eval_auc": 0.5,
      "eval_f1": 0.4745762711864407,
      "eval_loss": 0.2973339259624481,
      "eval_precision": 0.9032258064516129,
      "eval_recall": 1.0,
      "eval_runtime": 1.1837,
      "eval_samples_per_second": 157.138,
      "eval_steps_per_second": 5.069,
      "step": 28
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 1.603426218032837,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 0.2231,
      "step": 30
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9032258064516129,
      "eval_auc": 0.5,
      "eval_f1": 0.4745762711864407,
      "eval_loss": 0.3274933993816376,
      "eval_precision": 0.9032258064516129,
      "eval_recall": 1.0,
      "eval_runtime": 1.1347,
      "eval_samples_per_second": 163.913,
      "eval_steps_per_second": 5.288,
      "step": 35
    },
    {
      "epoch": 5.714285714285714,
      "grad_norm": 1.8515961170196533,
      "learning_rate": 2.380952380952381e-05,
      "loss": 0.1791,
      "step": 40
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9032258064516129,
      "eval_auc": 0.5,
      "eval_f1": 0.4745762711864407,
      "eval_loss": 0.31467387080192566,
      "eval_precision": 0.9032258064516129,
      "eval_recall": 1.0,
      "eval_runtime": 1.1182,
      "eval_samples_per_second": 166.344,
      "eval_steps_per_second": 5.366,
      "step": 42
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8978494623655914,
      "eval_auc": 0.5218253968253969,
      "eval_f1": 0.5205535205535206,
      "eval_loss": 0.34014198184013367,
      "eval_precision": 0.907103825136612,
      "eval_recall": 0.9880952380952381,
      "eval_runtime": 1.1252,
      "eval_samples_per_second": 165.308,
      "eval_steps_per_second": 5.333,
      "step": 49
    },
    {
      "epoch": 7.142857142857143,
      "grad_norm": 1.4963322877883911,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 0.1361,
      "step": 50
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7849462365591398,
      "eval_auc": 0.5833333333333335,
      "eval_f1": 0.5528846153846154,
      "eval_loss": 0.3884872794151306,
      "eval_precision": 0.9210526315789473,
      "eval_recall": 0.8333333333333334,
      "eval_runtime": 1.1007,
      "eval_samples_per_second": 168.985,
      "eval_steps_per_second": 5.451,
      "step": 56
    },
    {
      "epoch": 8.571428571428571,
      "grad_norm": 2.6748523712158203,
      "learning_rate": 7.936507936507936e-06,
      "loss": 0.1245,
      "step": 60
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8817204301075269,
      "eval_auc": 0.5873015873015872,
      "eval_f1": 0.6011695906432748,
      "eval_loss": 0.31924736499786377,
      "eval_precision": 0.9195402298850575,
      "eval_recall": 0.9523809523809523,
      "eval_runtime": 1.117,
      "eval_samples_per_second": 166.524,
      "eval_steps_per_second": 5.372,
      "step": 63
    },
    {
      "epoch": 10.0,
      "grad_norm": 3.4235951900482178,
      "learning_rate": 0.0,
      "loss": 0.0902,
      "step": 70
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8225806451612904,
      "eval_auc": 0.6041666666666667,
      "eval_f1": 0.5828746177370031,
      "eval_loss": 0.35260289907455444,
      "eval_precision": 0.9245283018867925,
      "eval_recall": 0.875,
      "eval_runtime": 1.1366,
      "eval_samples_per_second": 163.644,
      "eval_steps_per_second": 5.279,
      "step": 70
    },
    {
      "epoch": 10.0,
      "step": 70,
      "total_flos": 1.1375723808188006e+18,
      "train_loss": 0.21184425609452384,
      "train_runtime": 168.3293,
      "train_samples_per_second": 52.041,
      "train_steps_per_second": 0.416
    }
  ],
  "logging_steps": 10,
  "max_steps": 70,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 1.1375723808188006e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}