allenai/tk-instruct-base-def-pos model fined tuned on custom pyabsa english model from 'ATEPC_MULTILINGUAL_CHECKPOINT' auto annotated hospital reviews [keywords,polarity] dataset.
Training Results:
Epoch | Training Loss | Validation Loss
1 | 0.061900 | 0.047395
2 | 0.038300 | 0.035213
3 | 0.029700 | 0.028486
4 | 0.024900 | 0.028562
Evaluation Results:
Train Precision: 0.9682688696958318
Train Recall: 0.9692090837901332
Train F1: 0.968738748610698
Test Precision: 0.965
Test Recall: 0.9620517768129925
Test F1: 0.9635236331427651
UnseenTest Precision: 0.9670502092050209
UnseenTest Recall: 0.9685699319015191
UnseenTest F1: 0.9678094739596965
- Downloads last month
- 1