fine-tuning with evaluator
#20
by
praveensonu
- opened
Hi, I'd like to fine tune reranker v2 with an evaluator (example, triplet loss or reranker loss in this case?) . but the script - https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker
doesnt contain how to finetune with an evaluator for early stopping. could you please let me know how to do it? Thanks alot