Embedding warm-up
Connecting to the inference service…
Progress: CER per checkpoint
Greedy decoding of the full validation set: 50 crops per language (Urdu from gemini_urdu, Kashmiri from synth_kashmiri) + 50 arXiv pages (arXiv CER on text only, location tokens removed). CER per sample is capped at 100%, so one loop cannot dominate a mean; "Loops" = share of outputs that reach the token limit. Stock = the original Qwen3.5-4B with its own tokenizer; step 0 = our model before training (initialized new rows). Output tokens count with each model's own tokenizer. New checkpoints are read automatically. Lower is better.
Try a checkpoint
Boxes:
This sample over training
Predictions saved by the CER check, at each evaluated checkpoint.