trainer_state.json

{
  "best_metric": 0.7647058823529411,
  "best_model_checkpoint": "convnext-tiny-224-drfx-CT-classifier/checkpoint-4",
  "epoch": 10.0,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7647058823529411,
      "eval_loss": 0.6600015163421631,
      "eval_runtime": 0.1838,
      "eval_samples_per_second": 92.505,
      "eval_steps_per_second": 27.207,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5882352941176471,
      "eval_loss": 0.7135058045387268,
      "eval_runtime": 0.2157,
      "eval_samples_per_second": 78.8,
      "eval_steps_per_second": 23.177,
      "step": 8
    },
    {
      "epoch": 2.5,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.4055,
      "step": 10
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6470588235294118,
      "eval_loss": 0.6851004958152771,
      "eval_runtime": 0.1807,
      "eval_samples_per_second": 94.088,
      "eval_steps_per_second": 27.673,
      "step": 12
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6470588235294118,
      "eval_loss": 0.6512044668197632,
      "eval_runtime": 0.1486,
      "eval_samples_per_second": 114.416,
      "eval_steps_per_second": 33.652,
      "step": 16
    },
    {
      "epoch": 5.0,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.3895,
      "step": 20
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6470588235294118,
      "eval_loss": 0.7130866646766663,
      "eval_runtime": 0.1511,
      "eval_samples_per_second": 112.526,
      "eval_steps_per_second": 33.096,
      "step": 20
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6470588235294118,
      "eval_loss": 0.7157571315765381,
      "eval_runtime": 0.1508,
      "eval_samples_per_second": 112.708,
      "eval_steps_per_second": 33.149,
      "step": 24
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7647058823529411,
      "eval_loss": 0.6532735228538513,
      "eval_runtime": 0.1506,
      "eval_samples_per_second": 112.877,
      "eval_steps_per_second": 33.199,
      "step": 28
    },
    {
      "epoch": 7.5,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.363,
      "step": 30
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.7058823529411765,
      "eval_loss": 0.6210929155349731,
      "eval_runtime": 0.1672,
      "eval_samples_per_second": 101.678,
      "eval_steps_per_second": 29.905,
      "step": 32
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7647058823529411,
      "eval_loss": 0.6221739649772644,
      "eval_runtime": 0.1853,
      "eval_samples_per_second": 91.73,
      "eval_steps_per_second": 26.979,
      "step": 36
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0,
      "loss": 0.3207,
      "step": 40
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.7647058823529411,
      "eval_loss": 0.6255453824996948,
      "eval_runtime": 0.1847,
      "eval_samples_per_second": 92.059,
      "eval_steps_per_second": 27.076,
      "step": 40
    },
    {
      "epoch": 10.0,
      "step": 40,
      "total_flos": 1.608168860024832e+16,
      "train_loss": 0.36969062089920046,
      "train_runtime": 46.5,
      "train_samples_per_second": 13.763,
      "train_steps_per_second": 0.86
    }
  ],
  "max_steps": 40,
  "num_train_epochs": 10,
  "total_flos": 1.608168860024832e+16,
  "trial_name": null,
  "trial_params": null
}