lrat-qwen3-0.6b-earlystop-full-20260723 – AI Model by Seraphic663 | AlphaNeural AI

You can deploy this model and start earning money today!

Seraphic663/
lrat-qwen3-0.6b-earlystop-full-20260723

like

0

feature-extraction

text-embeddings-inference

information-retrieval

Yuqi-Zhou/LRAT-Train

Qwen/Qwen3-Embedding-0.6B

endpoints_compatible

Views

No views yet

LRAT Qwen3 Embedding 0.6B — M07

This is the M07 retrieval model prepared for the CCIR Cup / LRAT evaluation. It is a full-parameter fine-tune of Qwen/Qwen3-Embedding-0.6B.

Training

Data: 94,113 official LRAT training rows after deterministic normalized-query separation
Training length: one epoch, 11,764 optimizer steps
Per-device batch size: 1 on two GPUs
Gradient accumulation: 4
Learning rate: 1e-6
External training data, teacher models, LoRA, and adapters: not used

The separated development set contains 1,500 normalized-query groups with zero query overlap with training.

Development metrics

Metric	Value
Recall@1	0.626667
Recall@5	0.907333
Recall@10	0.974667
MRR	0.747510

These are candidate-set development metrics, not official leaderboard results.

Integrity

model.safetensors SHA-256:

c937d61d57840467c5b8867559cc645704313e97ace7dafdeeece52652986a2b