license: cc-by-nc-4.0
allenai/tk-instruct-base-def-pos model fined tuned on custom KeyBert default keywords extracter model - all-MiniLM-L6-v2 and ABSA model - yangheng/deberta-v3-base-absa-v1.1 auto annotated hospital reviews [keywords,polarity] dataset.
Training Results:
Epoch | Training Loss | Validation Loss
1 | 0.150800 | 0.112104
2 | 0.103700 | 0.074400
3 | 0.074500 | 0.065034
4 | 0.065900 | 0.062676
5 | 0.059700 | 0.058017
6 | 0.050700 | 0.056635
7 | 0.046500 | 0.056589
8 | 0.046300 | 0.056924
Evaluation Results:
Train Precision: 0.9552227554840818
Train Recall: 0.9552107544443746
Train F1: 0.9552167549265339
Test Precision: 0.9300919842312746
Test Recall: 0.9301530981010578
Test F1: 0.9301225401622918
UnseenTest Precision: 0.9329632792485055
UnseenTest Recall: 0.9329632792485055
UnseenTest F1: 0.9329632792485054