python run_t5_mlm_flax.py \ | |
--output_dir="./marathi-t5-base" \ | |
--model_type="t5" \ | |
--config_name="./marathi-t5-base" \ | |
--tokenizer_name="./marathi-t5-base" \ | |
--train_file="/home/nipunsadvilkar/mr_data/mr_train_punctrm.csv" \ | |
--validation_split_percentage=7 \ | |
--max_seq_length="512" \ | |
--per_device_train_batch_size="32" \ | |
--per_device_eval_batch_size="32" \ | |
--adafactor \ | |
--learning_rate="0.005" \ | |
--weight_decay="0.001" \ | |
--warmup_steps="2000" \ | |
--overwrite_output_dir \ | |
--logging_steps="100" \ | |
--save_steps="1000" \ | |
--eval_steps="1000" | |