glue-rte-bert-base-uncased – AI Model by asun17904 | AlphaNeural AI

You can deploy this model and start earning money today!

asun17904/
glue-rte-bert-base-uncased

like

0

Views

No views yet

Plainly Optimized Network

Dataset: GLUE

Trainer Hyperparameters:

lr = 5e-05
per_device_batch_size = 32
gradient_accumulation_steps = 1
weight_decay = 0.0
seed = 42

eval_loss	eval_accuracy	epoch
21.354	0.531	1.0
20.627	0.621	2.0
20.929	0.610	3.0
21.703	0.585	4.0
21.829	0.581	5.0
21.040	0.635	6.0
21.964	0.585	7.0
21.910	0.581	8.0
22.344	0.581	9.0