docs/results/hf_training_status.json

{
  "status": "running",
  "started_at": 1777141590.5730433,
  "finished_at": null,
  "commands": [
    {
      "args": [
        "python",
        "scripts/bootstrap_data.py"
      ],
      "returncode": 0,
      "elapsed_seconds": 0.82
    },
    {
      "args": [
        "python",
        "scripts/build_training_corpus.py",
        "--profile",
        "massive",
        "--with-local",
        "--with-synthetic",
        "--with-hf"
      ],
      "returncode": 0,
      "elapsed_seconds": 4.259
    },
    {
      "args": [
        "python",
        "scripts/train_sft_trl.py",
        "--model-id",
        "Qwen/Qwen2.5-0.5B-Instruct",
        "--epochs",
        "1",
        "--max-steps",
        "20",
        "--batch-size",
        "2",
        "--max-seq-len",
        "512",
        "--use-unsloth"
      ],
      "returncode": 0,
      "elapsed_seconds": 1.885
    },
    {
      "args": [
        "python",
        "scripts/train_grpo_trl.py",
        "--model-id",
        "Qwen/Qwen2.5-0.5B-Instruct",
        "--max-prompts",
        "0",
        "--max-steps",
        "0",
        "--epochs",
        "1",
        "--batch-size",
        "2",
        "--num-generations",
        "2",
        "--max-prompt-length",
        "384",
        "--max-completion-length",
        "64",
        "--use-unsloth"
      ],
      "returncode": 1,
      "elapsed_seconds": 286.177
    }
  ],
  "artifact_repo_id": "TheJackBright/polyguard-openenv-training-artifacts"
}