Codex 2ea14bd465 docs(model): training results addendum for LoRA sentiment + emotion ...

- FinBERT: 5 epochs, early stop at ~4.8, 6.2MB, F1=0.907, acc=0.955
- DistilRoBERTa: 5 epochs, early stop at ~4.8, 8.1MB, F1=0.594, acc=0.865
- Both with early stopping (patience=3)
- Known issues documented for next iteration

2026-09-26 19:59:56 +02:00

..

config

feat(sentiment): add 30 new sources for uncovered trade assets

2026-09-25 14:47:44 +02:00

src/sentiment_engine/nlp

fix(nlp): reliable model loading with parallel init + timeout handling

2026-09-26 15:44:47 +02:00

training

feat(training): LoRA sentiment + emotion pipelines complete

2026-09-26 19:58:48 +02:00

MODEL_CARD_TRAINING_STATUS.md

docs(model): training results addendum for LoRA sentiment + emotion

2026-09-26 19:59:56 +02:00