metadata
language: en
license: mit
library_name: pytorch
Plainly Optimized Network
Dataset: BIGBENCH
Trainer Hyperparameters:
lr
= 5e-05per_device_batch_size
= 8gradient_accumulation_steps
= 2weight_decay
= 0.0seed
= 42
eval_loss | eval_accuracy | epoch |
---|---|---|
10.410 | 0.571 | 1.0 |
10.191 | 0.571 | 2.0 |
9.468 | 0.643 | 3.0 |