mobilebert_add_GLUE_Experiment_logit_kd_wnli

This model is a fine-tuned version of google/mobilebert-uncased on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3478	1.0	5	0.3460	0.5634
0.3477	2.0	10	0.3480	0.4366
0.3466	3.0	15	0.3459	0.5634
0.3466	4.0	20	0.3448	0.5634
0.3468	5.0	25	0.3451	0.5634
0.3467	6.0	30	0.3461	0.5634
0.3465	7.0	35	0.3465	0.5634
0.3466	8.0	40	0.3466	0.5634
0.3468	9.0	45	0.3457	0.5634

Loading…