| export RUN_NAME=two_latent | |
| ./venv/bin/python train.py \ | |
| --t5_model_name_or_path="t5-base" \ | |
| --output_dir="output/${RUN_NAME}" \ | |
| --overwrite_output_dir \ | |
| --dataset_name="Fraser/python-lines" \ | |
| --do_train --do_eval \ | |
| --n_latent_tokens 2 \ | |
| --latent_token_size 16 \ | |
| --save_steps="2500" \ | |
| --eval_steps="2500" \ | |
| --block_size="32" \ | |
| --per_device_train_batch_size="10" \ | |
| --per_device_eval_batch_size="10" \ | |
| --overwrite_output_dir \ | |
| --num_train_epochs="1" \ | |
| --push_to_hub \ | |