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