- ++model=iic/SenseVoiceSmall - ++trust_remote_code=true - ++train_data_set_list=/root/autodl-tmp/train/train.jsonl - ++valid_data_set_list=/root/autodl-tmp/val/val.jsonl - ++dataset_conf.data_split_num=1 - ++dataset_conf.batch_sampler=BatchSampler - ++dataset_conf.batch_size=25000 - ++dataset_conf.sort_size=1024 - ++dataset_conf.batch_type=token - ++dataset_conf.num_workers=4 - ++train_conf.max_epoch=100 - ++train_conf.log_interval=1 - ++train_conf.resume=true - ++train_conf.validate_interval=2000 - ++train_conf.save_checkpoint_interval=2000 - ++train_conf.keep_nbest_models=10 - ++train_conf.avg_nbest_model=10 - ++train_conf.use_deepspeed=false - ++train_conf.deepspeed_config=/root/autodl-tmp/SenseVoice/deepspeed_conf/ds_stage1.json - ++optim_conf.lr=0.0002 - ++output_dir=./outputs