Qwen3-4B Stage-3 NCE โ temp07-perround variant
Stage-3 Noise-Contrastive-Estimation training resumed from the Stage-2
end ckpt at step 7335. NCE phase trains the scorer head to rank K=4
candidate completions per block. Differs from beam-perround in proposal
sampling: this variant uses softmax_sampling at proposal_temperature
=0.7 (vs argmax in beam-perround) โ closer to training-time scorer
noise.
Files
| File | Size |
|---|---|
model.pt |
8.5 GB |
optimizer.pt |
0.45 GB |
scheduler.pt |
1.7 KB |
eval_batches.pt |
13 MB |
rng_rank{0..23}.pt |
14.7 KB each |
Total: ~9.54 GB / 30 files. Full resume state for re-training.
Step + lineage
- Resume from: Stage-2 ckpt at step 7335
- This ckpt: step 9124 (1789 NCE-phase steps)
- Proposal:
combine=softmax_sampling,proposal_temperature=0.7 - Config:
configs/large_scale/qwen3_4b_stage3_nce_resume7335_temp07_perround_6n.yaml
Note on inference reproducibility
When evaluating this ckpt, use:
combine=softmax_sampling proposal_temperature=0.7
to MATCH the training distribution. Using combine=beam_bayes argmax
(as for the perround/lastround variants) on this ckpt produces an
out-of-distribution scorer signal.
Related archives
haotiansun014/qwen3-4b-stage3-nce-7335-perround-archivehaotiansun014/qwen3-4b-stage3-nce-7335-lastround-archive
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support