| python run_mlm_flax_stream.py \ | |
| --model_name_or_path="xlm-roberta-base" \ | |
| --config_name="./config.json" \ | |
| --tokenizer_name="./" \ | |
| --dataset_name="NbAiLab/NCC_plus_scandi" \ | |
| --max_seq_length="512" \ | |
| --weight_decay="0.01" \ | |
| --per_device_train_batch_size="56" \ | |
| --per_device_eval_batch_size="16" \ | |
| --learning_rate="2e-4" \ | |
| --warmup_steps="25000" \ | |
| --overwrite_output_dir \ | |
| --num_train_steps="250000" \ | |
| --adam_beta1="0.9" \ | |
| --adam_beta2="0.98" \ | |
| --logging_steps="500" \ | |
| --save_steps="10000" \ | |
| --eval_steps="10000" \ | |
| --output_dir="./" \ | |
| --dtype="bfloat16" \ | |
| --hub_model_id="NbAiLab/nb-roberta-base-ncc-plus-scandi" \ | |
| --push_to_hub | |