The following hyperparameters were used during training:
learning_rate: 0.0002 train_batch_size: 3 eval_batch_size: 8 seed: 42
gradient_accumulation_steps: 2 total_train_batch_size: 6
optimizer: Adam with betas=(0.9,0.999)
and epsilon=1e-08 lr_scheduler_type: constant lr_scheduler_warmup_ratio: 0.03
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 0.0002
train_batch_size: 3
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 6
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
