Commit History

  1. Document per-case score and verdict files

    Verified signature
    4fda809
  2. Add per-case scores and per-criterion judge verdicts

    Verified signature
    e98071d
  3. Add per-case scores and per-criterion judge verdicts

    Verified signature
    0753c39

  1. Remove superseded partial-rubric artifacts

    Verified signature
    154f089
  2. Remove superseded partial-rubric artifacts

    Verified signature
    58d5e63
  3. Remove superseded partial-rubric artifacts

    Verified signature
    2f48f07
  4. Add full V5.9.2 evaluation artifacts

    Verified signature
    7562182
  5. Add full V5.9.2 evaluation artifacts

    Verified signature
    4b4a4e4
  6. Add full V5.9.2 evaluation artifacts

    Verified signature
    51aa93b
  7. Add full V5.9.2 evaluation artifacts

    Verified signature
    c5124d3
  8. Add full V5.9.2 evaluation artifacts

    Verified signature
    84df4f3
  9. Update to full V5.9.2 scores (all three rubric families, n=200)

    Verified signature
    456ff9e

  1. Add evaluator models (9B step100, 27B step296): checkpoints, benchmark, usage

    Verified signature
    dfa1204
  2. Add designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/model.safetensors

    Verified signature
    21d3433
  3. Add designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/trainer_state.json

    Verified signature
    f4b22d1
  4. Add designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/trainer_log.jsonl

    Verified signature
    23799ae
  5. Add designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/tokenizer_config.json

    Verified signature
    f07d007
  6. Add designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/tokenizer.json

    Verified signature
    e8588eb
  7. Add designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/processor_config.json

    Verified signature
    5cb25cd
  8. Add designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/generation_config.json

    Verified signature
    f6a98cb
  9. Add designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/config.json

    Verified signature
    07b013a
  10. Add designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/chat_template.jinja

    Verified signature
    2e8f98a
  11. Add designcoder_evaluator_qwen3.5_9b_adamw_bs256_data37847_step100/README.md

    Verified signature
    d72282d
  12. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/model-00002-of-00002.safetensors

    Verified signature
    d9e81c6
  13. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/model-00001-of-00002.safetensors

    Verified signature
    9632c81
  14. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/training_loss.png

    Verified signature
    42ca276
  15. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/trainer_state.json

    Verified signature
    a7ae526
  16. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/trainer_log.jsonl

    Verified signature
    3ea479e
  17. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/tokenizer_config.json

    Verified signature
    2750a04
  18. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/tokenizer.json

    Verified signature
    87ea98a
  19. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/processor_config.json

    Verified signature
    c2e2ec0
  20. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/model.safetensors.index.json

    Verified signature
    56815e3
  21. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/generation_config.json

    Verified signature
    81ae21d
  22. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/config.json

    Verified signature
    84f7a65
  23. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/chat_template.jinja

    Verified signature
    e17ed36
  24. Add designcoder_evaluator_qwen3.8_27b_adamw_bs256_data37847_step296/README.md

    Verified signature
    fc0a557
  25. Add full-run HTML report (4 models x 200 cases)

    Verified signature
    a9e2060
  26. Add eval artifacts: summary, per-case scores, significance tests, rubric stats, HTML report

    Verified signature
    eb98c6f
  27. Add eval artifacts: summary, per-case scores, significance tests, rubric stats, HTML report

    Verified signature
    d48d53f
  28. Add eval artifacts: summary, per-case scores, significance tests, rubric stats, HTML report

    Verified signature
    153178d
  29. Add eval artifacts: summary, per-case scores, significance tests, rubric stats, HTML report

    Verified signature
    d441fde
  30. Update bench-200 final full-run scores (n=200 all models) + eval artifacts

    Verified signature
    b6cd8e0

  1. Update model card: add 4 data41287 checkpoints, fix dataset revision, add bench-200 scores

    Verified signature
    5721771
  2. Add designcoder_qwen3.8_27b_adamw_bs128_data41287_step400 (bench-200: 91.19, strongest in release)

    Verified signature
    3c6d824
  3. Add designcoder_qwen3.5_9b_adamw_bs256_data41287_step200 (bench-200: 84.40)

    Verified signature
    90876b3
  4. Add designcoder_qwen3.5_4b_muon_bs256_data41287_step200 (bench-200: 83.36)

    Verified signature
    a080534
  5. Add designcoder_qwen3.5_4b_adamw_bs256_data41287_step200 (bench-200: 84.22)

    Verified signature
    05c92d6

  1. Update model card: drop removed 9B ep20 arm

    Verified signature
    827032f
  2. Remove 9B ep20 over-training arm

    Verified signature
    c9a4cf3
  3. Update model card: drop removed 27B arm, add weight decay column, generalize naming rule

    Verified signature
    b0d6d7d