john/folksy_idioms
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
folksy_idioms/scripts
History
Exact
john 02daa7bb97 Add SFT training script and run Qwen3-0.6B-Base fine-tune 
Train Qwen3-0.6B-Base (596M params) on 36K folksy proverb pairs
using full SFT with HuggingFace TRL. 3 epochs, 11 min on RTX 4090.

Results: train_loss=0.954, eval_loss=1.032, test_loss=1.031
Model checkpoint at folksy-model/final/ (not committed — 1.2 GB)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-31 22:07:23 -04:00
..
classify_proverbs.py Initial 'folksy idiom' generator 2026-02-15 14:04:25 -05:00
compute_corpus_stats.py corpus generation (work from mid february) 2026-03-09 19:52:09 -04:00
enhance_graph.py corpus generation (work from mid february) 2026-03-09 19:52:09 -04:00
expand_vocab.py corpus generation (work from mid february) 2026-03-09 19:52:09 -04:00
extract_from_conceptnet.py Initial 'folksy idiom' generator 2026-02-15 14:04:25 -05:00
extract_relations.py Initial 'folksy idiom' generator 2026-02-15 14:04:25 -05:00
filter_corpus.py corpus generation (work from mid february) 2026-03-09 19:52:09 -04:00
format_training_pairs.py corpus generation (work from mid february) 2026-03-09 19:52:09 -04:00
generate_raw_batch.sh Fix generator quality issues and run initial corpus pipeline 2026-03-10 04:33:56 -04:00
naturalize_corpus.py Add naturalization pass — 9,025 sayings, 36K training pairs 2026-03-10 07:24:37 -04:00
polish_corpus.py Fix generator quality issues and run initial corpus pipeline 2026-03-10 04:33:56 -04:00
rebuild_training_pairs.py Add naturalization pass — 9,025 sayings, 36K training pairs 2026-03-10 07:24:37 -04:00
train_sft.py Add SFT training script and run Qwen3-0.6B-Base fine-tune 2026-03-31 22:07:23 -04:00