asun17904
/

glue-qqp-t5-base

Model card Files Files and versions Community

Edit model card

Plainly Optimized Network

Dataset: GLUE

Trainer Hyperparameters:

lr = 5e-05
per_device_batch_size = 16
gradient_accumulation_steps = 1
weight_decay = 1e-09
seed = 42

eval_loss	eval_accuracy	epoch
13.188	0.896	1.0
13.060	0.901	2.0

Downloads last month: 0

Unable to determine this model’s pipeline type. Check the docs .