You can deploy this model and start earning money today!

gokuls/
hBERTv2_new_pretrain_48_emb_com_qnli

Name: hBERTv2_new_pretrain_48_emb_com_qnli
Availability: InStock

Views

No views yet

hBERTv2_new_pretrain_48_emb_com_qnli

This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_emb_compress_48 on the GLUE QNLI 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:

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7033	1.0	819	0.7265	0.5054
0.6988	2.0	1638	0.6937	0.4946
0.6969	3.0	2457	0.6934	0.4946
0.6951	4.0	3276	0.6945	0.4946
0.6944	5.0	4095	0.6963	0.5054
0.6944	6.0	4914	0.6946	0.5054
0.6945	7.0	5733	0.6959	0.4946
0.6943	8.0	6552	0.6931	0.5054
0.6938	9.0	7371	0.6937	0.5054
0.6939	10.0	8190	0.6944	0.4946
0.6936	11.0	9009	0.6940	0.4946
0.6937	12.0	9828	0.6933	0.4946
0.6937	13.0	10647	0.6987	0.4946