You can deploy this model and start earning money today!

gokuls/
hBERTv1_new_pretrain_w_init_48_rte

Name: hBERTv1_new_pretrain_w_init_48_rte
Availability: InStock

Views

No views yet

hBERTv1_new_pretrain_w_init_48_rte

This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48 on the GLUE RTE 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
0.712	1.0	20	0.7158	0.4729
0.7094	2.0	40	0.6958	0.4729
0.7025	3.0	60	0.7008	0.4729
0.705	4.0	80	0.6919	0.5271
0.7023	5.0	100	0.6960	0.5271
0.7002	6.0	120	0.7095	0.4729
0.7071	7.0	140	0.7040	0.4729
0.6982	8.0	160	0.6918	0.5271
0.7025	9.0	180	0.6910	0.5271
0.6965	10.0	200	0.6984	0.4621
0.6814	11.0	220	0.7635	0.4946
0.6616	12.0	240	0.6918	0.5271
0.6658	13.0	260	0.7622	0.5307
0.6316	14.0	280	0.8002	0.5090