---
language: en
license: mit
library_name: pytorch
---
# Plainly Optimized Network
Dataset: BIGBENCH

Trainer Hyperparameters:
- `lr` = 5e-05
- `per_device_batch_size` = 1
- `gradient_accumulation_steps` = 4
- `weight_decay` = 1e-09
- `seed` = 42

|eval_loss|eval_accuracy|epoch|
|--|--|--|
|64.996|0.062|1.0|
|54.188|0.048|2.0|