{
  "base_model": "sky_v1_3_5_5b_sky_runtime",
  "curriculum_dir": "csd-dataset",
  "final_dir": "sky_v1_3_csd_final",
  "total_minutes": 11.612064441045126,
  "stages": [
    {
      "train_runtime": 330.6326,
      "train_samples_per_second": 2.767,
      "train_steps_per_second": 0.172,
      "train_loss": 1.0252654144638462,
      "epoch": 0.9967213114754099,
      "stage": "stage1_scaffold",
      "minutes": 5.513923645019531,
      "train_rows": 915,
      "val_rows": 58,
      "learning_rate": 5e-07,
      "epochs": 1.0
    },
    {
      "train_runtime": 205.8567,
      "train_samples_per_second": 5.446,
      "train_steps_per_second": 0.34,
      "train_loss": 1.0430820686476572,
      "epoch": 0.9991079393398751,
      "stage": "stage2_bridge",
      "minutes": 3.435288441181183,
      "train_rows": 1121,
      "val_rows": 71,
      "learning_rate": 5e-07,
      "epochs": 1.0
    },
    {
      "train_runtime": 116.6573,
      "train_samples_per_second": 5.803,
      "train_steps_per_second": 0.36,
      "train_loss": 0.8398375312487284,
      "epoch": 0.9926144756277696,
      "stage": "stage3_clean",
      "minutes": 1.9487456480662029,
      "train_rows": 677,
      "val_rows": 43,
      "learning_rate": 4e-07,
      "epochs": 1.0
    }
  ]
}