---
{}
---
# TRAINING ARGS:
{'per_device_train_batch_size': 16,
 'warmup_ratio': 0.1,
 'num_train_epochs': 1}

# OPTIMIZER ARGS:
{'lr': 0.001, 'eps': (1e-30, 0.001), 'clip_threshold': 1.0, 'decay_rate': 0.0, 'beta1': None, 'weight_decay': 0.0, 'scale_parameter': False, 'relative_step': False, 'warmup_init': False, 'differentiable': False}

# DEVICE:
NVIDIA A100 80GB PCIe