ocr_pilot100k
, trained on L4 (AWS, spot). .
Hypothesis
Bulk OCR of about 100,000 scanned pages (127 books) with OCR-VLM v1 on spot GPUs.
What we learned
Runs in short spot sessions that resume page by page.
Scores
No scores published yet.
Curves
No training curves were published for this run.Its scores above are what it published.
Model
- Preset
- —
- Parameters
- —
- Outside embeddings
- —
- Layers · heads · width
- — · — · —
- Tokenizer
- —
Data
- Slice
- —
- Words
- —
- Training tokens
- —
- Passes
- —
- Tokens seen
- —
Compute
- GPU
- L4
- Where
- AWS (spot)
- Steps
- —
- GPU hours
- —
- Cost
- $28.55
- Spot restarts
- 1
Lineage
awsspot