Fine tuned sparse BERT base to MNLI (GLUE Benchmark) task from bert-base-uncased-sparse-70-unstructured.
This model doesn't have a classifier layer to enable easier loading of the model for training to other downstream tasks. In all the other layers this model is similar to bert-base-uncased-mnli-sparse-70-unstructured.
Note: This model requires
Matched: 82.5% Mismatched: 83.3%
This model can be further fine-tuned to other tasks and achieve the following evaluation results:
|Task||QQP (Acc/F1)||QNLI (Acc)||SST-2 (Acc)||STS-B (Pears/Spear)||SQuADv1.1 (Acc/F1)|
- Downloads last month