Indonesian QEA for Public Figure in News Article with BERT
Collection
9 items
•
Updated
This model is a fine-tuned version of indolem/indobertweet-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
Train Loss | Validation Loss | Validation F1 | Validation Accuracy | Epoch |
---|---|---|---|---|
0.3339 | 0.2405 | 0.7705 | 0.9215 | 0 |
0.2057 | 0.2222 | 0.8239 | 0.9262 | 1 |
0.1616 | 0.2319 | 0.8432 | 0.9281 | 2 |
0.1264 | 0.2350 | 0.8509 | 0.9273 | 3 |
0.1012 | 0.2632 | 0.8507 | 0.9272 | 4 |
Base model
indolem/indobertweet-base-uncased