You can deploy this model and start earning money today!

Yxanul/
yx49k-l20-checkpoints

Name: yx49k-l20-checkpoints
Availability: InStock

apache-2.0

Views

No views yet

yx49k-l20 post-training checkpoint lineage

Private custody of every checkpoint of record from the GOLD/SFT post-training arc (kda_hybrid_yx49k_l20, 308M params, yx49k tokenizer, base = ClimbMix pretrain step 700,000). Each folder holds the SFT-stage state.pkl (fp32 params + muonclip optimizer, nnx pure-dict pickle) and metadata.json where available.

folder	lineage	IFEval mean	panel
sft-mephisto-v2-1200	gen-2 SFT (690k IF+Knowledge rows @2048)	40.4	10/42
gold-if10k-151	gen-2 + GOLD 10k IF	42.1	-
gold-if50k-759	gen-2 + GOLD 50k IF	48.4	12/42
gold-mix300k-4449	gen-2 + GOLD 100k IF+100k Knowledge+100k MathCode	51.0	16/42
sft-mix6m-2000	base + SFT 6.27M rows @4096, step 2000 mid-save	-	-
sft-mix6m-4000	base + SFT 6.27M rows @4096, checkpoint of record	35.3	15/42
gold-over-sft-1ep-1575	sft-mix6m-4000 + GOLD 1 epoch, 1/3 mix, K=32	41.3	22/42
gold-over-sft-2ep-3150	same, 2 epochs (epoch scaling null)	40.3	22/42

Full experiment record: post_training/GOLD.md and results/ in the yxTPU repo. Teacher: Qwen3.5-4B. Restore path: nnx.replace_by_pure_dict into a TrainStateNNX built from the kda_hybrid_yx49k_l20 config.

Yxanul/yx49k-l20-checkpoints

yx49k-l20 post-training checkpoint lineage

Yxanul/
yx49k-l20-checkpoints