---
license: mit
base_model: jspaulsen/halluci-mate-v2b
language:
- en
tags:
- chess
- dpo
- uci
- qwen
pipeline_tag: text-generation
---

# halluci-mate v2d

DPO fine-tune of [`jspaulsen/halluci-mate-v2b`](https://huggingface.co/jspaulsen/halluci-mate-v2b)
on a broadened Stockfish-vs-model preference set. Same Qwen3-0.6B architecture,
same custom ~1,800-token UCI tokenizer. v2d revisits the export filters used for
[v2c](https://huggingface.co/jspaulsen/halluci-mate-v2c) and improves on it across
nearly every vs-Stockfish axis.

Source: https://github.com/jspaulsen/halluci-mate

## What changed vs v2c

The training recipe and base model are identical to v2c. Only the preference
dataset changed, along three axes of the `export-dpo` filter:

| | v2c | **v2d** |
|---|---|---|
| `--flavor` | `quality` | `both` (adds legality pairs) |
| `--threshold` | 200 cp | **300 cp** (sharper blunder definition) |
| `--require-consequential` | on | **off** (keeps blunders from already-lost positions) |
| `--exclude-repetition` | on | **off** |
| Pairs | 11,491 | **25,717** |

The hypothesis going in: dropping `--require-consequential` should help the
model learn to keep losing positions losing rather than swindle, and the
threshold-300 cut should reduce label noise by only counting genuinely sharp
blunders. The vs-Stockfish results below validate that hypothesis, especially
in endgame and lost-position phases. The legality-pair re-inclusion is an
incidental change in the same direction that we did not isolate separately.

## Training data

25,717 preference pairs derived from the same 10,000-game v2b-vs-Stockfish run
used for v2c (skill 5, depth 12), exported via the
[halluci-mate](https://github.com/jspaulsen/halluci-mate) eval harness:

```
scripts/eval.py export-dpo <run> --flavor both --threshold 300
```

## Training recipe

[`scripts/train_dpo.py`](https://github.com/jspaulsen/halluci-mate/blob/main/scripts/train_dpo.py)
via TRL's `DPOTrainer` — same hyperparameters as v2c:

| | |
|---|---|
| Method | DPO (TRL) |
| Base / reference model | `jspaulsen/halluci-mate-v2b` |
| Pairs | 25,717 (98% train / 2% eval) |
| Learning rate | 1e-5 |
| LR schedule | cosine, 5% warmup |
| Beta | 0.1 |
| Epochs | 2 (trained), checkpoint-500 selected (≈1.27 ep) |
| Per-device batch × grad accum × GPUs | 16 × 2 × 2 = effective 64 |
| Optimizer | paged AdamW 8-bit |
| Precision | bf16 + flash-attention-2 |
| Total steps | 788 (full run); shipped checkpoint at step 500 |
| Hardware | RTX PRO 4500 Blackwell + RTX 3090 (DDP) |

Step 500 was selected post-hoc as the first checkpoint to hit the maximum
`eval_rewards/accuracies` on the held-out split. As with v2c, `eval_loss`
keeps falling and `eval_rewards/margins` keeps growing through later steps
while accuracy plateaus — empirically the later checkpoints are behaviorally
worse on vs-Stockfish.

## Held-out eval at end of training (step 500)

Note: v2d's eval split contains both legality and quality pairs at threshold
300, so these numbers are not directly comparable to v2c's held-out numbers.

| metric | value |
|---|---|
| eval_loss | 0.6431 |
| eval_rewards/accuracies | 0.8438 |
| eval_rewards/margins | 0.1086 |

## vs-Stockfish (skill 5, depth 12, alternating colors, `--sf-analyze`, 100 games)

| metric | v2c | **v2d** | Δ |
|---|---|---|---|
| score_rate | 0.085 | 0.090 | +0.5pp (within n=100 noise) |
| legal_rate | 0.9755 | **0.9826** | +0.71pp |
| tactical_oversight_rate | 0.1437 | **0.1363** | -0.74pp |
| blunder_rate (overall) | 0.0616 | **0.0570** | -0.46pp |
| blunder_rate (consequential) | 0.0483 | 0.0504 | +0.21pp |
| blunder_rate (lost positions) | 0.0795 | **0.0658** | -1.37pp |
| blunder_rate (endgame) | 0.0811 | **0.0714** | -0.97pp |
| CPL p95 (overall) | 253 | **233** | -20cp |

score_rate is within the n=100 noise band; per-move quality improvements on
tactical_oversight, blunder rate (especially endgame and lost positions),
and CPL tail are above noise and consistent with the broadened, sharper
preference set.

## License

MIT, matching the v2b base.