Last active
November 17, 2019 22:51
-
-
Save xelibrion/574078eafd59f28af45467bf0c078ca2 to your computer and use it in GitHub Desktop.
Prodigy ner.batch-train
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env bash | |
| set -e | |
| TRAIN_DATASETS="re-tag-keyphrases-zoey,lyft-0-50-gold" | |
| EVAL_DATASETS="re-tag-keyphrases-dmitry,lyft-50-100-gold" | |
| FINAL_TRAIN="train-$(date +%s)" | |
| FINAL_EVAL="eval-$(date +%s)" | |
| MODEL_NAME="model-$(date +%s)" | |
| prodigy db-merge $TRAIN_DATASETS $FINAL_TRAIN | |
| prodigy db-merge $EVAL_DATASETS $FINAL_EVAL | |
| prodigy ner.batch-train \ | |
| $FINAL_TRAIN en_vectors_web_lg \ | |
| -n 100 --batch-size 16 --unsegmented --no-missing \ | |
| -l KEYPHRASE \ | |
| -e $FINAL_EVAL -o $MODEL_NAME | |
| prodigy drop $FINAL_TRAIN | |
| prodigy drop $FINAL_EVAL |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment