{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiezuhlsymtxroespwiboboqouy4hn6qsjunmgegy2fwbp3qnsxq7u",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mmexfepyuku2"
  },
  "path": "/t/date-format-for-tine-tuning-ai-models/176116#post_5",
  "publishedAt": "2026-05-21T15:36:19.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "Unfortunately it didn’t work out. My fine-tuned model is still making up invalid dates. I’m beginning to think the issue lies elsewhere outside the scope of date formats. I’ll keep digging!\n\nI should add that I have witnessed this issue across the board while fine-tuning several QwenX.X and LlamaX.X models using SFT. I have traced the tokenizing of the dates and displayed the trainer’s batch input-ids right before starting training. They matched the dates found in the dataset.",
  "title": "Date format for tine-tuning AI models"
}