text-summarization / params.yaml
hakim
model trainer added
f2492e6
raw
history blame
235 Bytes
TrainingArguments:
num_train_epochs: 1
warmup_steps: 500
per_device_train_batch_size: 1
weight_decay: 0.01
logging_steps: 10
evaluation_strategy: steps
eval_steps: 500
save_steps: 1e6
gradient_accumulation_steps: 16